INDEX

Explanations

phrases containing specific abbreviations 'ac' followed by a number related to academic or medical references

oai_token-act-pair · gpt-3.5-turbo

variations of the prefix "ac-" which often relate to acceleration or academic concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vous

-0.94

ĸļ

-0.75

hof

-0.74

 Dare

-0.71

 Stur

-0.70

wich

-0.67

eker

-0.66

 Burk

-0.66

Kuh

-0.66

 Huckabee

-0.66

POSITIVE LOGITS

rylic

1.16

oustic

1.14

celer

1.06

ademic

1.01

emia

0.92

emies

0.89

ric

0.89

atech

0.88

upuncture

0.88

acia

0.87

Activations Density 0.020%

phrases containing specific abbreviations 'ac' followed by a number related to academic or medical references

variations of the prefix "ac-" which often relate to acceleration or academic concepts

No Comments

No Known Activations