INDEX

Explanations

mentions of specific names or proper nouns

oai_token-act-pair · gpt-3.5-turbo

names and references to specific individuals or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rum

-0.84

mented

-0.81

matically

-0.80

 glim

-0.77

 shenan

-0.73

rers

-0.71

ging

-0.71

fully

-0.71

pse

-0.70

ged

-0.70

POSITIVE LOGITS

tera

0.92

terday

0.73

alon

0.72

xual

0.72

 Centauri

0.71

bian

0.70

oulos

0.68

odus

0.67

ylon

0.67

uclear

0.65

Activations Density 0.028%

mentions of specific names or proper nouns

names and references to specific individuals or entities

No Comments

No Known Activations