INDEX

Explanations

numerical values or approximate estimates

oai_token-act-pair · gpt-3.5-turbo

estimations or approximations in numerical descriptions

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

Negative Logits

chens

-0.80

oly

-0.76

ses

-0.75

NEY

-0.70

achus

-0.69

chen

-0.68

 Writ

-0.68

Write

-0.67

ATH

-0.66

 Peaks

-0.65

POSITIVE LOGITS

 halfway

0.78

 midway

0.76

aleb

0.73

PsyNetMessage

0.70

pron

0.69

abama

0.67

capacity

0.67

 triv

0.66

pheus

0.66

 dozen

0.65

Activations Density 0.074%

numerical values or approximate estimates

estimations or approximations in numerical descriptions

No Known Activations