INDEX

Explanations

phrases indicating decision-making or conclusion

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the action of presenting or putting something forward for consideration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 pregnancies

-0.68

artifacts

-0.64

holder

-0.63

 withdrawals

-0.61

notations

-0.61

 empt

-0.59

scl

-0.59

important

-0.58

hops

-0.56

 employed

-0.56

POSITIVE LOGITS

lling

0.86

lled

0.86

ggles

0.81

wered

0.80

pload

0.77

 fend

0.77

pless

0.77

 blame

0.71

othy

0.69

OOL

0.69

Activations Density 0.098%

phrases indicating decision-making or conclusion

phrases indicating the action of presenting or putting something forward for consideration

No Comments

No Known Activations