INDEX

Explanations

words related to fast, automatic physical responses or reactions

oai_token-act-pair · gpt-3.5-turbo

words related to reflexes and quick responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

holder

-0.78

########

-0.77

################

-0.73

akin

-0.69

 Shining

-0.65

rooms

-0.63

rug

-0.62

ATTLE

-0.62

 unpublished

-0.62

enery

-0.61

POSITIVE LOGITS

 reflex

1.33

ively

1.14

entimes

1.02

 Reflex

0.94

 guiActiveUn

0.93

ibly

0.86

ive

0.84

es

0.81

ologically

0.80

osate

0.79

Activations Density 0.006%

words related to fast, automatic physical responses or reactions

words related to reflexes and quick responses

No Comments

No Known Activations