INDEX

Explanations

mentions of fictional elements or settings

oai_token-act-pair · gpt-3.5-turbo

mentions of fictional elements or settings within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ktop

-0.86

hammad

-0.82

gans

-0.75

cler

-0.74

ikk

-0.72

acks

-0.72

ni

-0.70

feeding

-0.70

xual

-0.69

trust

-0.69

POSITIVE LOGITS

istically

1.01

 fictional

1.01

ãĤ¼ãĤ¦ãĤ¹

0.92

acters

0.91

 portray

0.90

 universes

0.89

 recre

0.88

ized

0.88

 portrayal

0.84

 depictions

0.81

Activations Density 0.013%

mentions of fictional elements or settings

mentions of fictional elements or settings within a narrative

No Comments

No Known Activations