INDEX

Explanations

mentions of the name "Alison" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or entities, particularly names and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

llular

-0.95

alion

-0.81

uristic

-0.80

 Daytona

-0.76

dk

-0.76

enegger

-0.74

poral

-0.74

sburgh

-0.73

rano

-0.72

inal

-0.71

POSITIVE LOGITS

ĸļ

0.94

 Alison

0.94

terness

0.89

 Weir

0.85

 Grimes

0.76

ĺħ

0.71

 Shir

0.71

 Koen

0.71

 Wonderland

0.68

 wolves

0.68

Activations Density 0.020%

mentions of the name "Alison" in various contexts

references to specific individuals or entities, particularly names and brands

No Comments

No Known Activations