INDEX

Explanations

words related to speed or rate of change

oai_token-act-pair · gpt-3.5-turbo

adverbs that indicate speed or intensity of actions

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

tein

-0.68

izoph

-0.64

oln

-0.64

vous

-0.64

cknowled

-0.63

icion

-0.61

 History

-0.61

ription

-0.56

oute

-0.56

oked

-0.56

POSITIVE LOGITS

 srfAttach

0.98

 during

0.76

 because

0.76

 throughout

0.76

 onstage

0.75

(>

0.72

aneously

0.71

 unnoticed

0.70

 thereafter

0.70

 afterward

0.70

Activations Density 0.217%

words related to speed or rate of change

adverbs that indicate speed or intensity of actions

No Comments

No Known Activations