INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Joan."

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

nut

-0.73

rals

-0.68

phrine

-0.68

ï¸ı

-0.66

rave

-0.65

ork

-0.63

NESS

-0.63

regulated

-0.63

mented

-0.62

ropolitan

-0.62

POSITIVE LOGITS

 Joan

0.80

naire

0.75

Anne

0.74

Rei

0.72

 Crawford

0.72

nee

0.72

ja

0.72

Doe

0.72

istic

0.70

 Hamm

0.70

Activations Density 0.030%

proper nouns

mentions of the name "Joan."

No Comments

No Known Activations