INDEX

Explanations

references to political discussions or commentary

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

ngdoc

-0.77

 فريبيس

-0.66

rukt

-0.65

ztály

-0.63

 resourceCulture

-0.63

%</

-0.62

Atentamente

-0.60

OGND

-0.58

 prioridad

-0.57

kaufs

-0.57

POSITIVE LOGITS

Apparently

0.64

 apparently

0.63

 ostensibly

0.61

apparently

0.61

 Apparently

0.60

ICY

0.58

 yesterday

0.55

onomía

0.55

 folks

0.53

FWIW

0.53

Activations Density 0.455%

references to political discussions or commentary

No Comments

No Known Activations