INDEX

Explanations

names of a particular person, potentially related to various contexts or locations

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific person named Watts

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

ozo

-0.72

anthrop

-0.71

arial

-0.69

ournal

-0.68

 issuer

-0.66

ruct

-0.66

ablo

-0.65

 Lyft

-0.65

oral

-0.63

ptive

-0.63

POSITIVE LOGITS

atts

1.22

nesday

1.03

ukong

0.95

itness

0.90

esley

0.86

 Watts

0.85

ithing

0.84

halla

0.84

enberg

0.83

idth

0.80

Activations Density 0.030%

names of a particular person, potentially related to various contexts or locations

mentions of a specific person named Watts

No Comments

No Known Activations