INDEX

Explanations

numeric values in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

脚注の使い方

-0.99

findpost

-0.96

ⓧ

-0.95

 مشين

-0.88

Билгалдахарш

-0.88

PYX

-0.87

 intptr

-0.84

/*

-0.81

awtextra

-0.78

 '\\;'

-0.77

POSITIVE LOGITS

0.56

0.51

 ciudadana

0.48

0.42

********

0.41

0.40

******

0.39

 öğretmen

0.39

*********

0.38

Activations Density 0.173%

numeric values in the text

No Comments

No Known Activations