INDEX

Explanations

proper nouns related to names and places

oai_token-act-pair · gpt-3.5-turbo

names and terms related to sirens and individuals involved in narratives about emergencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

secondary

-0.78

ĵĺ

-0.77

eneg

-0.74

reating

-0.74

poral

-0.74

ole

-0.72

erity

-0.71

staking

-0.70

 unnecess

-0.69

intosh

-0.69

POSITIVE LOGITS

izen

1.16

iren

1.09

FTWARE

0.85

 Chaser

0.85

nings

0.84

HEAD

0.84

~~~~

0.80

irens

0.78

OPLE

0.77

BIT

0.77

Activations Density 0.018%

proper nouns related to names and places

names and terms related to sirens and individuals involved in narratives about emergencies

No Comments

No Known Activations