INDEX

Explanations

phrases related to utility or functionality

oai_token-act-pair · gpt-3.5-turbo

the word "with" in various contexts

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

chuk

-0.66

sov

-0.65

FFFF

-0.65

nery

-0.63

schild

-0.62

ischer

-0.61

etts

-0.59

iations

-0.59

omsky

-0.58

marg

-0.58

POSITIVE LOGITS

draw

1.14

 regards

1.09

 regard

1.04

drawn

1.03

stood

0.99

 impunity

0.94

 respect

0.91

standing

0.84

holding

0.80

 Hits

0.78

Activations Density 0.077%

phrases related to utility or functionality

the word "with" in various contexts

No Comments

No Known Activations