INDEX

Explanations

mentions of scars and scar-related terms

oai_token-act-pair · gpt-3.5-turbo

references to "scar" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ablishment

-0.72

ĨĴ

-0.70

hower

-0.68

ostics

-0.64

odcast

-0.63

£ı

-0.62

ullivan

-0.62

imates

-0.61

eers

-0.61

Luk

-0.61

POSITIVE LOGITS

red

1.16

ring

1.13

lets

1.06

lett

1.03

let

0.96

fed

0.96

crow

0.96

uler

0.95

ves

0.94

abs

0.92

Activations Density 0.042%

mentions of scars and scar-related terms

references to "scar" and its variations in context

No Comments

No Known Activations