INDEX

Explanations

numeric values and their occurrences in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 present

-0.60

est

-0.60

ı

-0.60

ANGEL

-0.59

 eens

-0.59

 Nuss

-0.58

儿

-0.56

 Sommers

-0.54

wale

-0.54

ycz

-0.54

POSITIVE LOGITS

AndEndTag

1.21

1.11

AddTagHelper

0.89

awtextra

0.89

+#+#

0.84

 Catto

0.78

webElementXpaths

0.78

 ſeveral

0.76

 defaultstate

0.75

RegressionTest

0.73

Activations Density 0.865%

numeric values and their occurrences in text

No Comments

No Known Activations