INDEX

Explanations

specific terms represented by the letter 'X' followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to specific model names or designations in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

getic

-0.81

assetsadobe

-0.73

 respons

-0.71

,,,,,,,,

-0.70

 à¤

-0.69

inally

-0.67

è¦ļéĨĴ

-0.66

Ð¼

-0.66

kson

-0.66

Tot

-0.64

POSITIVE LOGITS

avier

1.08

peria

1.04

III

1.03

0.96

xon

0.95

ML

0.94

cellence

0.92

BOX

0.91

XT

0.91

IX

0.91

Activations Density 0.015%

specific terms represented by the letter 'X' followed by a number

references to specific model names or designations in a technical context

No Comments

No Known Activations