INDEX

Explanations

scenes or locations mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

references to scenes in movies or productions

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

achev

-0.83

amn

-0.82

berman

-0.82

izo

-0.79

wegian

-0.78

icrobial

-0.77

heit

-0.77

itude

-0.77

secut

-0.75

ces

-0.74

POSITIVE LOGITS

 scenes

1.44

 Scenes

1.29

scenes

0.96

 Scene

0.94

Dialogue

0.86

 scene

0.82

 dramas

0.81

scene

0.81

 depicting

0.73

 portrayal

0.73

Activations Density 0.005%

scenes or locations mentioned in a text

references to scenes in movies or productions

No Comments

No Known Activations