INDEX

Explanations

terms related to the entertainment industry

oai_token-act-pair · gpt-3.5-turbo

references to the entertainment industry

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

gs

-0.69

ioxide

-0.68

agher

-0.66

elled

-0.65

eled

-0.63

ennett

-0.61

eding

-0.60

 broken

-0.60

opher

-0.60

ignt

-0.60

POSITIVE LOGITS

tainment

1.01

 entertainment

0.97

NZ

0.80

Sav

0.77

 Tonight

0.76

Center

0.70

 outlet

0.70

Club

0.69

 Enterprises

0.68

Services

0.68

Activations Density 0.009%

terms related to the entertainment industry

references to the entertainment industry

No Comments

No Known Activations