INDEX

Explanations

references to various entities or concepts within sentences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "reference" and its variations

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

keye

-0.73

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.69

alach

-0.67

awk

-0.67

cffff

-0.66

Â¯Â¯Â¯Â¯

-0.66

iolet

-0.66

ihad

-0.65

DAQ

-0.65

ongyang

-0.65

POSITIVE LOGITS

ibly

0.91

 references

0.89

ibility

0.86

enza

0.81

IBLE

0.76

 thereto

0.73

 therein

0.71

 Neph

0.70

 referencing

0.69

NRS

0.69

Activations Density 0.021%

references to various entities or concepts within sentences

instances of the word "reference" and its variations

No Comments

No Known Activations