INDEX

Explanations

names or terms related to specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic or political contexts

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

ampires

-0.73

 slightest

-0.72

 bugs

-0.69

 whiff

-0.67

 outnumbered

-0.65

adish

-0.64

 prostitutes

-0.63

 mosquitoes

-0.63

 stains

-0.63

 lowly

-0.63

POSITIVE LOGITS

igsaw

0.95

 endeavour

0.90

 repertoire

0.89

 continuum

0.83

 effort

0.83

 regimen

0.82

yssey

0.78

 curriculum

0.78

 strategy

0.77

issance

0.76

Activations Density 0.350%

names or terms related to specific individuals or entities

references to specific geographic or political contexts

No Comments

No Known Activations