INDEX

Explanations

terms related to actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.56

-0.43

 Vertrauen

-0.42

 picioare

-0.42

henko

-0.42

 shall

-0.41

↵

-0.40

recht

-0.39

了

-0.39

POSITIVE LOGITS

LookAnd

1.15

Portale

1.00

TagMode

0.92

twimg

0.89

WebVitals

0.85

 دیکھیے

0.83

 Signalez

0.79

 lenker

0.79

Jeografia

0.78

 kiệm

0.78

Activations Density 0.419%

terms related to actions or processes

No Comments

No Known Activations