INDEX

Explanations

mentions of a specific TV show

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific television show or its episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undai

-0.73

ntil

-0.71

srf

-0.69

 solitary

-0.67

 disag

-0.67

etheless

-0.65

 incapac

-0.64

ilateral

-0.63

 Klux

-0.63

 diss

-0.62

POSITIVE LOGITS

runners

1.42

runner

1.40

biz

1.37

manship

1.17

mable

1.07

 airs

1.00

girls

0.95

wright

0.91

room

0.90

girl

0.86

Activations Density 0.031%

mentions of a specific TV show

mentions of a specific television show or its episodes

No Comments

No Known Activations