INDEX

Explanations

names of superheroes and related words such as crazy, shy, and lol

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

references to superheros or characters in popular culture

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nered

-0.69

 endpoint

-0.67

 veil

-0.66

âĶĢâĶĢ

-0.66

ast

-0.66

 cryptoc

-0.65

 counselling

-0.65

 vigil

-0.64

 immersion

-0.64

 accommodation

-0.64

POSITIVE LOGITS

 Legs

1.08

Dick

1.01

 Pants

1.00

 Hipp

0.97

 Patty

0.95

Dave

0.94

 Pete

0.94

 Bastard

0.93

 Mouth

0.92

Joe

0.91

Activations Density 0.208%

names of superheroes and related words such as crazy, shy, and lol

references to superheros or characters in popular culture

No Known Activations