INDEX

Explanations

words related to the word "pen"

oai_token-act-pair · gpt-3.5-turbo

the term "pen" in various contexts

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

 thirds

-0.77

enance

-0.76

LM

-0.65

aspx

-0.63

 hitch

-0.62

 BIOS

-0.62

perse

-0.62

 Afric

-0.61

kernel

-0.61

Hep

-0.60

POSITIVE LOGITS

insula

1.43

cil

1.21

itent

1.20

ultimate

1.03

chant

1.02

pen

0.97

issance

0.95

elope

0.95

alties

0.94

ning

0.91

Activations Density 0.011%

words related to the word "pen"

the term "pen" in various contexts

No Comments

No Known Activations