INDEX

Explanations

excerpts related to vocal expression, such as yelling and swearing

oai_token-act-pair · gpt-3.5-turbo

words related to forms of storytelling or relaying information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pei

-0.81

vi

-0.69

FIX

-0.67

Le

-0.66

MED

-0.65

veh

-0.65

office

-0.65

Repl

-0.64

mun

-0.63

nec

-0.63

POSITIVE LOGITS

ĸļ

0.88

enance

0.76

ength

0.76

hetti

0.74

yond

0.73

uations

0.73

amination

0.73

uca

0.73

enburg

0.70

 Aires

0.69

Activations Density 0.013%

excerpts related to vocal expression, such as yelling and swearing

words related to forms of storytelling or relaying information

No Comments

No Known Activations