INDEX

Explanations

questions ending in a question mark

oai_token-act-pair · gpt-3.5-turbo

questions that seek clarification or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

nery

-0.74

ald

-0.74

hed

-0.74

 Rodrig

-0.70

geons

-0.69

plet

-0.69

 herself

-0.67

 McMaster

-0.67

leground

-0.66

hing

-0.66

POSITIVE LOGITS

?????-?????-

1.06

Answer

0.98

ccording

0.90

?????-

0.89

è¦ļéĨĴ

0.87

OVA

0.86

Unit

0.83

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.79

Vari

0.78

Generally

0.78

Activations Density 0.162%

questions ending in a question mark

questions that seek clarification or information

No Comments

No Known Activations