INDEX

Explanations

the name "Katie" followed by a single letter or a surname

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Katie" or similar variations

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

dfx

-0.85

interstitial

-0.82

ional

-0.81

reed

-0.81

lict

-0.80

netflix

-0.79

istry

-0.76

asks

-0.73

itent

-0.73

pmwiki

-0.72

POSITIVE LOGITS

Kat

1.01

 Cour

0.98

Pav

0.93

 Katie

0.88

 Nolan

0.87

 Holmes

0.84

kat

0.84

 Upton

0.83

rina

0.82

 Hopkins

0.81

Activations Density 0.007%

the name "Katie" followed by a single letter or a surname

mentions of the name "Katie" or similar variations

No Comments

No Known Activations