INDEX

Explanations

words related to actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

words or phrases that indicate embarrassment or discomfort

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enegger

-0.66

 Moroc

-0.52

 Shining

-0.51

 nomine

-0.50

Untitled

-0.50

 conclud

-0.49

ONSORED

-0.48

 Webster

-0.48

TBA

-0.48

Interstitial

-0.48

POSITIVE LOGITS

anc

0.70

ip

0.66

ape

0.66

ims

0.65

ipp

0.65

ith

0.63

amin

0.63

amp

0.62

asing

0.62

ase

0.62

Activations Density 0.436%

words related to actions or behaviors

words or phrases that indicate embarrassment or discomfort

No Comments

No Known Activations