INDEX

Explanations

mentions of someone or something being featured or highlighted in various contexts or media

oai_token-act-pair · gpt-3.5-turbo

instances of the word "featured" in various contexts

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

sis

-0.92

alty

-0.79

Ã§a

-0.74

thur

-0.72

ignt

-0.71

ersion

-0.69

vernment

-0.69

utral

-0.69

ellig

-0.68

bey

-0.66

POSITIVE LOGITS

 prominently

1.46

Featured

0.85

pages

0.74

features

0.73

 featured

0.73

 Include

0.72

 Features

0.72

Feature

0.71

ãĤ´

0.71

 Featured

0.69

Activations Density 0.018%

mentions of someone or something being featured or highlighted in various contexts or media

instances of the word "featured" in various contexts

No Comments

No Known Activations