INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of places and people

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

TPP

-0.70

VICE

-0.70

 facult

-0.69

European

-0.66

 latex

-0.66

 compan

-0.65

 countdown

-0.65

Introdu

-0.64

dyl

-0.64

 admins

-0.63

POSITIVE LOGITS

 Heights

1.59

 Township

1.54

stown

1.53

 Hills

1.52

ville

1.51

 Valley

1.41

 Creek

1.40

 Junction

1.39

vale

1.37

 County

1.37

Activations Density 0.289%

locations or places

proper nouns, specifically names of places and people

No Comments

No Known Activations