INDEX

Explanations

mentions of a specific television show

oai_token-act-pair · gpt-3.5-turbo

references to a specific television show

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ntil

-0.79

orget

-0.68

 steel

-0.68

 granite

-0.68

xon

-0.65

 stone

-0.62

ilateral

-0.62

quez

-0.61

jri

-0.61

 clot

-0.60

POSITIVE LOGITS

runner

1.54

runners

1.53

biz

1.14

manship

1.00

Netflix

0.97

 premiered

0.94

 Hulu

0.93

wright

0.92

 airs

0.88

creator

0.87

Activations Density 0.059%

mentions of a specific television show

references to a specific television show

No Comments

No Known Activations