INDEX

Explanations

words related to scenes or settings in a story

oai_token-act-pair · gpt-3.5-turbo

references to specific scenes in media

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orem

-0.85

thood

-0.80

achev

-0.80

rition

-0.78

dp

-0.77

berman

-0.75

reditary

-0.75

heit

-0.72

ikarp

-0.72

gements

-0.72

POSITIVE LOGITS

Dialogue

1.02

 scenes

0.95

Capture

0.94

 unfolding

0.92

 Scenes

0.92

 involving

0.87

 depicting

0.80

 Scene

0.79

scene

0.75

 depicted

0.75

Activations Density 0.036%

words related to scenes or settings in a story

references to specific scenes in media

No Comments

No Known Activations