INDEX

Explanations

references to Wikipedia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orno

-0.56

 Leland

-0.55

 testify

-0.54

^{

-0.54

 màn

-0.53

 Dooley

-0.53

 Mota

-0.52

 firms

-0.51

 stuff

-0.50

 headless

-0.50

POSITIVE LOGITS

msub

3.79

msup

2.59

msubsup

2.29

erover

1.47

AddTagHelper

1.25

 nahilalakip

1.16

mfrac

1.15

ftagPool

1.01

AddHtmlAttribute

0.99

}")

0.92

Activations Density 0.064%

references to Wikipedia

No Comments

No Known Activations