INDEX

Explanations

references to antagonists or villains in a narrative context

oai_token-act-pair · gpt-3.5-turbo

terms related to villains in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

galitarian

-0.77

sterdam

-0.73

changes

-0.73

ollen

-0.73

glas

-0.72

oday

-0.71

chedel

-0.70

ª

-0.70

ikk

-0.69

arel

-0.68

POSITIVE LOGITS

ous

1.21

 villain

1.03

 Bane

1.01

ously

1.00

 villains

0.95

 mastermind

0.94

 lair

0.83

 antagonist

0.79

OUS

0.76

 Dracula

0.76

Activations Density 0.073%

references to antagonists or villains in a narrative context

terms related to villains in narratives

No Comments

No Known Activations