INDEX

Explanations

numerical values in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

'{@

-0.57

 löytyy

-0.56

 jät

-0.51

gonic

-0.51

labus

-0.50

ensively

-0.50

 löyty

-0.49

RTEX

-0.49

PreAuthorize

-0.48

cdk

-0.47

POSITIVE LOGITS

\%

0.80

\%$

0.64

\%)

0.64

$+

0.61

\&

0.60

ᅠ

0.58

\%

0.58

$)

0.58

$}

0.58

$+

0.57

Activations Density 0.017%

numerical values in various contexts

No Comments

No Known Activations