INDEX

Explanations

the word or partial word "rel" with a high activation

oai_token-act-pair · gpt-3.5-turbo

variations of the word "relate."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĥ¼ãĥĨãĤ£

-0.70

 Gael

-0.64

 Slate

-0.62

RIC

-0.61

 Methods

-0.60

theless

-0.59

 Sinn

-0.59

err

-0.58

sonian

-0.58

 Annotations

-0.58

POSITIVE LOGITS

aunch

1.46

apsed

1.33

ocating

1.29

apses

1.27

aun

1.24

atable

1.19

ocations

1.17

apse

1.17

aying

1.16

abel

1.13

Activations Density 0.013%

the word or partial word "rel" with a high activation

variations of the word "relate."

No Comments

No Known Activations