INDEX

Explanations

mentions of locations or entities in sentences

oai_token-act-pair · gpt-3.5-turbo

references to specific places, events, or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

dan

-0.93

-0.83

VII

-0.82

vi

-0.81

VE

-0.81

-0.80

uce

-0.80

Area

-0.79

vit

-0.78

POSITIVE LOGITS

 Bung

0.79

catentry

0.77

 Back

0.77

 Hicks

0.77

Mug

0.76

 funnel

0.76

 Haley

0.76

 Gree

0.75

oola

0.75

 Jung

0.75

Activations Density 0.319%

mentions of locations or entities in sentences

references to specific places, events, or classifications

No Comments

No Known Activations