INDEX

Explanations

answers to various questions or inquiries

oai_token-act-pair · gpt-3.5-turbo

phrases indicating conclusions or responses to questions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

drawn

-0.65

geries

-0.62

Represent

-0.59

wana

-0.57

 recol

-0.57

TIT

-0.57

 timet

-0.56

ãĥīãĥ©

-0.55

artney

-0.55

 Bulgar

-0.55

POSITIVE LOGITS

 depends

0.87

 answer

0.81

 lies

0.81

undrum

0.78

is

0.78

 seems

0.76

isn

0.75

 consists

0.75

uitive

0.75

 emerges

0.75

Activations Density 0.046%

answers to various questions or inquiries

phrases indicating conclusions or responses to questions

No Comments

No Known Activations