INDEX

Explanations

verbs related to movement or operation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "run" and its variations in different contexts

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

 Plain

-0.68

ighter

-0.64

ayers

-0.64

iden

-0.63

actory

-0.62

grave

-0.61

 Flavoring

-0.60

axter

-0.60

alam

-0.60

ault

-0.58

POSITIVE LOGITS

around

0.86

gs

0.84

dy

0.80

 concurrently

0.79

lasses

0.78

cul

0.78

estones

0.78

aways

0.78

Disney

0.76

 smoothly

0.76

Activations Density 0.047%

verbs related to movement or operation

occurrences of the word "run" and its variations in different contexts

No Comments

No Known Activations