INDEX

Explanations

comparative terms and descriptions of size or quantity

oai_token-act-pair · gpt-3.5-turbo

terms related to measurements or quantities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ERSON

-0.62

igl

-0.59

errilla

-0.58

 Borough

-0.55

_-_

-0.55

Engineers

-0.54

ffiti

-0.54

çĶ°

-0.53

qt

-0.53

uay

-0.53

POSITIVE LOGITS

 allowable

0.72

ebted

0.65

 nodd

0.64

 status

0.63

ucing

0.60

 substrate

0.60

 axis

0.60

 permissible

0.58

 particles

0.58

 payoff

0.57

Activations Density 1.107%

comparative terms and descriptions of size or quantity

terms related to measurements or quantities

No Known Activations