INDEX

Explanations

phrases describing common occurrences or characteristics

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate common occurrences or characteristics

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

eworld

-0.73

nut

-0.71

ys

-0.69

fix

-0.64

 Moral

-0.63

worms

-0.63

adra

-0.63

mosp

-0.62

stuff

-0.62

nuts

-0.62

POSITIVE LOGITS

CHAT

0.85

atility

0.73

DAQ

0.73

iences

0.73

eatures

0.72

utics

0.72

agonist

0.70

earable

0.70

ItemTracker

0.69

OLOGY

0.69

Activations Density 0.055%

phrases describing common occurrences or characteristics

phrases that indicate common occurrences or characteristics

No Comments

No Known Activations