INDEX

Explanations

mentions of the word "film" or variations of the word

oai_token-act-pair · gpt-3.5-turbo

references to the concept of film or filmmaking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ariat

-0.65

 rested

-0.63

 rests

-0.62

 upright

-0.62

 Standard

-0.59

 infant

-0.59

ometer

-0.58

 cradle

-0.58

 electrom

-0.58

 plummeted

-0.58

POSITIVE LOGITS

fil

4.02

Fil

2.81

Fil

2.00

film

1.81

FIL

1.71

FIL

1.62

filter

1.33

Film

1.32

 Films

1.29

Filter

1.15

Activations Density 0.006%

mentions of the word "film" or variations of the word

references to the concept of film or filmmaking

No Comments

No Known Activations