INDEX

Explanations

the word "this" followed by a description or statement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "this"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enty

-0.64

onto

-0.63

blown

-0.59

izont

-0.58

nown

-0.56

ometown

-0.56

pees

-0.56

doms

-0.55

ãĥ¼ãĥĨ

-0.54

adle

-0.54

POSITIVE LOGITS

 trope

0.91

 wiki

0.74

 Instruct

0.70

 particular

0.70

 article

0.70

 trait

0.69

 Quote

0.68

 archetype

0.68

 phrase

0.68

 poem

0.67

Activations Density 0.201%

the word "this" followed by a description or statement

instances of the word "this"

No Comments

No Known Activations