INDEX

Explanations

references to historical figures and their professional or personal backgrounds

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

 nakalista

-0.70

 referenties

-0.55

 مشين

-0.54

 ModelExpression

-0.50

IntoConstraints

-0.50

 "'",

-0.49

########.

-0.49

 Wiktionnaire

-0.48

 tegen

-0.46

urity

-0.46

POSITIVE LOGITS

 shoe

0.62

 sadd

0.58

 cooper

0.57

 boot

0.57

$_['

0.54

 Factors

0.54

oredCriteria

0.54

 TAIL

0.54

 méta

0.53

 Harness

0.53

Activations Density 0.440%

references to historical figures and their professional or personal backgrounds

No Comments

No Known Activations