INDEX

Explanations

phrases where the speaker is explaining or defining something

oai_token-act-pair · gpt-3.5-turbo

repeated phrases emphasizing personal experience or perspective

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 unsolved

-0.88

gettable

-0.83

Reviewer

-0.77

efeated

-0.73

uries

-0.72

MFT

-0.72

PDATE

-0.65

iscovered

-0.63

itaire

-0.62

 awaits

-0.61

POSITIVE LOGITS

 mean

1.63

 meant

1.45

 referring

1.45

 implying

1.34

 imply

1.33

 means

1.31

 refers

1.15

 refer

1.12

 referencing

1.10

meaning

1.09

Activations Density 0.376%

phrases where the speaker is explaining or defining something

repeated phrases emphasizing personal experience or perspective

No Comments

No Known Activations