INDEX

Explanations

the word "franchise" and its derivatives

oai_token-act-pair · gpt-3.5-turbo

references to franchises, specifically in the context of sports or entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

board

-0.81

ynthesis

-0.73

boards

-0.70

izoph

-0.70

ennett

-0.65

ools

-0.65

 Thou

-0.65

sonian

-0.63

hran

-0.62

afa

-0.61

POSITIVE LOGITS

eers

1.01

 cornerstone

0.79

atical

0.77

 franchise

0.76

rats

0.74

ally

0.73

 franchises

0.72

atics

0.72

ational

0.70

arily

0.69

Activations Density 0.041%

the word "franchise" and its derivatives

references to franchises, specifically in the context of sports or entertainment

No Comments

No Known Activations