INDEX

Explanations

phrases related to association, connection or relevance

oai_token-act-pair · gpt-3.5-turbo

connections or associations between different topics or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ifter

-0.83

aneers

-0.81

arer

-0.81

imates

-0.80

oufl

-0.76

\\\\\\\\

-0.76

ARD

-0.72

ardo

-0.71

ardless

-0.71

âķĲ

-0.70

POSITIVE LOGITS

 thereto

0.97

worldly

0.92

ness

0.91

 mater

0.81

 ancest

0.80

 unrelated

0.78

 additive

0.73

paren

0.73

lly

0.72

 topics

0.72

Activations Density 0.033%

phrases related to association, connection or relevance

connections or associations between different topics or concepts

No Comments

No Known Activations