INDEX

Explanations

mentions of the word "flick" or similar variations of the word

oai_token-act-pair · gpt-3.5-turbo

references to films and film-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mouth

-0.83

*/(

-0.79

isin

-0.72

large

-0.72

minist

-0.70

scient

-0.68

mia

-0.67

 Consortium

-0.66

LCS

-0.64

 Marketplace

-0.64

POSITIVE LOGITS

 flick

1.09

netflix

0.97

 films

0.95

licks

0.89

 film

0.87

Film

0.87

 movie

0.84

 movies

0.84

 Film

0.81

 Clint

0.79

Activations Density 0.027%

mentions of the word "flick" or similar variations of the word

references to films and film-related terms

No Comments

No Known Activations