INDEX

Explanations

mentions of specific proper nouns or brands

oai_token-act-pair · gpt-3.5-turbo

the word "One" and various pronouns and articles that suggest direct address or reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 slowing

-0.68

assetsadobe

-0.66

 nose

-0.66

 submar

-0.64

 dece

-0.64

 noses

-0.64

 vain

-0.63

 silenced

-0.63

 length

-0.62

 diver

-0.62

POSITIVE LOGITS

oran

0.89

lan

0.85

atson

0.85

zac

0.82

lins

0.79

alla

0.78

iba

0.78

chel

0.78

opolis

0.76

ussie

0.75

Activations Density 0.184%

mentions of specific proper nouns or brands

the word "One" and various pronouns and articles that suggest direct address or reference

No Comments

No Known Activations