INDEX

Explanations

mentions of memorable scenes from specific movies

oai_token-act-pair · gpt-3.5-turbo

references to or descriptions of scenes from movies or TV shows, particularly iconic moments or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

METHOD

-0.77

scl

-0.75

osponsors

-0.73

foreseen

-0.72

gression

-0.71

nington

-0.71

Statement

-0.70

erity

-0.70

jri

-0.69

 disag

-0.69

POSITIVE LOGITS

 movies

1.33

 sitcom

1.26

 movie

1.26

 films

1.23

 film

1.14

 Terminator

1.10

 flick

1.08

 Ghostbusters

1.07

 Movie

1.05

movie

1.05

Activations Density 0.377%

mentions of memorable scenes from specific movies

references to or descriptions of scenes from movies or TV shows, particularly iconic moments or characters

No Comments

No Known Activations