INDEX

Explanations

names or proper nouns

oai_token-act-pair · gpt-3.5-turbo

names of individuals or entities associated with the document's content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Haram

-0.75

âĶĢâĶĢ

-0.73

 underwater

-0.64

 Teddy

-0.61

 Border

-0.60

 respecting

-0.59

 Dangerous

-0.59

Â·Â·

-0.58

 tribal

-0.58

OPS

-0.58

POSITIVE LOGITS

elman

1.23

mons

1.21

mel

1.18

opoulos

1.16

ansky

1.14

pson

1.14

anski

1.13

inski

1.13

ayne

1.11

monds

1.08

Activations Density 0.099%

names or proper nouns

names of individuals or entities associated with the document's content

No Comments

No Known Activations