INDEX

Explanations

references to the name "Katz"

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ACTED

-0.81

FUL

-0.71

 dexter

-0.69

 insepar

-0.68

 miscarriage

-0.68

bably

-0.67

 abundantly

-0.64

NCT

-0.64

ridges

-0.64

LEASE

-0.63

POSITIVE LOGITS

atz

1.13

nik

1.00

inian

0.98

mann

0.94

azz

0.94

stein

0.94

tz

0.90

wald

0.90

hof

0.89

geist

0.89

Activations Density 0.009%

references to the name "Katz"

proper nouns, specifically names and entities

No Comments

No Known Activations