INDEX

Explanations

mentions of the word "documentary"

oai_token-act-pair · gpt-3.5-turbo

references to documentary films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cffff

-0.88

hare

-0.85

hap

-0.77

ymes

-0.77

Commerce

-0.72

sembly

-0.71

cream

-0.69

ingers

-0.69

efficients

-0.69

uckles

-0.68

POSITIVE LOGITS

 filmmaker

1.18

 documentary

1.06

 filmmakers

1.04

 filmmaking

1.02

 film

1.00

 documentaries

0.92

arily

0.90

film

0.88

arium

0.88

 films

0.85

Activations Density 0.039%

mentions of the word "documentary"

references to documentary films

No Comments

No Known Activations