INDEX

Explanations

scenes or sequences in a narrative

oai_token-act-pair · gpt-3.5-turbo

repetitions of the word "scene" and its context in relation to cinematic experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

orem

-0.89

rition

-0.79

achev

-0.77

berman

-0.74

dp

-0.73

iott

-0.73

thood

-0.72

reditary

-0.72

gements

-0.70

uyomi

-0.70

POSITIVE LOGITS

Dialogue

1.10

 involving

1.03

 depicting

0.96

 scenes

0.94

 unfolding

0.92

Capture

0.91

 Scenes

0.87

 depicted

0.87

 filmed

0.83

 unfold

0.82

Activations Density 0.043%

scenes or sequences in a narrative

repetitions of the word "scene" and its context in relation to cinematic experiences

No Comments

No Known Activations