INDEX

Explanations

phrases indicating a person or entity being at a specific location

oai_token-act-pair · gpt-3.5-turbo

references to locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 fundament

-0.71

rane

-0.67

thora

-0.62

Ī

-0.62

ACY

-0.59

livion

-0.57

rene

-0.56

//[

-0.56

tle

-0.55

ndra

-0.54

POSITIVE LOGITS

 testifying

1.09

 photograp

1.09

 discussing

1.09

 watching

1.09

 filming

1.08

 interviewing

1.06

 awaiting

1.06

 assisting

1.06

 preparing

1.05

 waiting

1.05

Activations Density 0.358%

phrases indicating a person or entity being at a specific location

references to locations or places

No Comments

No Known Activations