INDEX

Explanations

words related to preventing or hindering something, such as obstructing, thwarting, and impeding

oai_token-act-pair · gpt-3.5-turbo

gerunds and words that imply ongoing actions or processes

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

NetMessage

-0.41

©¶æ¥µ

-0.31

 mathemat

-0.30

ongyang

-0.30

wal

-0.29

ËĪ

-0.29

 WATCHED

-0.29

bats

-0.28

 bats

-0.28

wcs

-0.27

POSITIVE LOGITS

tenance

0.35

Initialized

0.33

INAL

0.33

èĢħ

0.31

 onward

0.31

ulous

0.31

 Adin

0.31

ENCY

0.30

iversary

0.30

 eternity

0.30

Activations Density 1.962%

words related to preventing or hindering something, such as obstructing, thwarting, and impeding

gerunds and words that imply ongoing actions or processes

No Comments

No Known Activations