INDEX

Explanations

mentions of historical events or contexts

oai_token-act-pair · gpt-3.5-turbo

references to historical events or concepts

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

vae

-0.73

rative

-0.73

ients

-0.72

rowd

-0.71

inki

-0.70

ched

-0.70

wer

-0.70

ividual

-0.70

utters

-0.69

ractive

-0.69

POSITIVE LOGITS

 history

1.20

 History

1.01

ISTORY

0.99

history

0.93

 histories

0.92

 Timeline

0.85

 Medals

0.79

 buffs

0.79

 record

0.76

 corpus

0.76

Activations Density 0.026%

mentions of historical events or contexts

references to historical events or concepts

No Comments

No Known Activations