INDEX

Explanations

food items

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating choices or options

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

anson

-0.79

minist

-0.78

issance

-0.76

IGHTS

-0.66

(%

-0.63

INAL

-0.63

Ãį

-0.62

 therap

-0.62

erness

-0.60

WAY

-0.60

POSITIVE LOGITS

etc

0.82

etc

0.66

Interstitial

0.64

Flo

0.60

 multim

0.59

 Snap

0.58

Flickr

0.57

 runners

0.57

 tuna

0.57

Activations Density 0.435%

food items

conjunctions and phrases indicating choices or options

No Comments

No Known Activations