INDEX

Explanations

references to specific political or cultural locations

oai_token-act-pair · gpt-3.5-turbo

mentions of notable locations and civic-related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

pret

-0.73

DI

-0.73

 craft

-0.71

 paddle

-0.67

craft

-0.66

 microbi

-0.65

 glob

-0.65

 modelling

-0.65

 Targ

-0.65

 Icelandic

-0.65

POSITIVE LOGITS

 Coliseum

3.87

iseum

1.74

 Civic

1.61

 Chavez

1.50

 Snapdragon

1.05

 Contra

1.01

 Alpine

0.97

grounds

0.96

 Auditor

0.94

parable

0.93

Activations Density 0.053%

references to specific political or cultural locations

mentions of notable locations and civic-related references

No Comments

No Known Activations