INDEX

Explanations

phrases related to lack of change or progress

oai_token-act-pair · gpt-3.5-turbo

terms related to evidence and indicators of trends or situations

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

eg

-0.66

ioxide

-0.62

ometimes

-0.61

tnc

-0.61

eals

-0.61

igs

-0.61

soType

-0.60

visor

-0.59

cin

-0.59

iets

-0.58

POSITIVE LOGITS

 whatsoever

1.93

nor

1.09

 anymore

1.02

 except

0.92

 unless

0.78

 anywhere

0.77

 necessarily

0.77

nor

0.74

except

0.71

 bothered

0.70

Activations Density 0.163%

phrases related to lack of change or progress

terms related to evidence and indicators of trends or situations

No Comments

No Known Activations