INDEX

Explanations

phrases related to actors starring in various movies and shows

oai_token-act-pair · gpt-3.5-turbo

the presence of phrases indicating roles in film or television

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

 learners

-0.83

llor

-0.77

 convol

-0.76

 incumb

-0.74

 incl

-0.67

 deterrent

-0.65

 lear

-0.63

pec

-0.62

 taught

-0.62

awei

-0.62

POSITIVE LOGITS

 lieu

1.22

 spite

1.08

animate

1.06

clus

1.04

 conjunction

1.04

 disguise

1.03

 accordance

0.99

 vain

0.99

strument

0.98

versions

0.97

Activations Density 0.519%

phrases related to actors starring in various movies and shows

the presence of phrases indicating roles in film or television

No Comments

No Known Activations