INDEX

Explanations

threatening or aggressive communication

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-0.59

UrlResolution

-0.58

الدراسه

-0.58

 ویکی‌پدیای

-0.55

pushFollow

-0.55

UnknownFieldSet

-0.52

\{\\

-0.52

]};

-0.51

esez

-0.51

ngdoc

-0.48

POSITIVE LOGITS

 retali

0.77

 retaliation

0.69

 deterrent

0.67

 vengeance

0.64

 revenge

0.64

 aven

0.61

✨:

0.59

 deterrence

0.56

hadiran

0.55

 uncin

0.55

Activations Density 0.319%

threatening or aggressive communication

No Comments

No Known Activations