INDEX

Explanations

phrases introducing general statements or observations

oai_token-act-pair · gpt-3.5-turbo

generalizing terms and phrases that imply common experiences or observations

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

 gent

-0.63

imm

-0.62

enting

-0.61

 nearby

-0.61

avering

-0.57

pron

-0.57

driving

-0.57

andering

-0.56

 chore

-0.56

 rapp

-0.56

POSITIVE LOGITS

entimes

0.87

chwitz

0.86

 Helpful

0.85

terness

0.83

eus

0.83

resy

0.82

 Strikes

0.82

 Issue

0.81

yip

0.77

 Called

0.77

Activations Density 0.032%

phrases introducing general statements or observations

generalizing terms and phrases that imply common experiences or observations

No Comments

No Known Activations