INDEX

Explanations

mentions of something unspecified but important or significant in the context

oai_token-act-pair · gpt-3.5-turbo

references to vague or unspecified entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

jad

-0.64

itative

-0.59

cent

-0.58

PC

-0.57

alde

-0.57

ort

-0.56

encing

-0.56

net

-0.56

 Nation

-0.55

umb

-0.55

POSITIVE LOGITS

 something

3.22

something

2.51

 somet

2.30

 Something

2.05

Something

1.97

 anything

1.71

 somebody

1.67

 someone

1.60

someone

1.51

anything

1.50

Activations Density 0.041%

mentions of something unspecified but important or significant in the context

references to vague or unspecified entities or concepts

No Comments

No Known Activations