INDEX

Explanations

measurements related to microns

oai_token-act-pair · gpt-3.5-turbo

references to microphones

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

 Anonymous

-0.72

 Spit

-0.71

tenance

-0.71

ACTED

-0.69

ENGTH

-0.69

apache

-0.67

ãģĦ

-0.65

ãĤĤ

-0.64

mberg

-0.64

OAD

-0.64

POSITIVE LOGITS

mic

1.23

roman

1.08

helle

0.93

HAEL

0.92

romancer

0.89

rom

0.88

ropolitan

0.87

olon

0.86

rones

0.86

rics

0.80

Activations Density 0.005%

measurements related to microns

references to microphones

No Comments

No Known Activations