INDEX

Explanations

proper names, possibly associated with criminal activity

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

itarian

-0.68

 corrid

-0.67

acious

-0.67

meric

-0.64

 therape

-0.64

 Moroc

-0.63

MAT

-0.60

ween

-0.60

 unden

-0.59

 mathemat

-0.58

POSITIVE LOGITS

igham

0.88

igger

0.79

LLP

0.74

ucker

0.73

 Township

0.70

umber

0.69

patrick

0.69

son

0.67

mare

0.67

 Dent

0.66

Activations Density 0.125%

proper names, possibly associated with criminal activity

proper nouns, particularly names

No Comments

No Known Activations