INDEX

Explanations

phrases that indicate conditions or limitations on actions or rights

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

ttemberg

-0.69

guenos

-0.63

ViewFeatures

-0.62

 ModelExpression

-0.61

EPIC

-0.60

cellaneous

-0.56

¡¡

-0.56

ariConfig

-0.56

··

-0.55

)))))

-0.55

POSITIVE LOGITS

 лишь

1.01

 merely

0.84

แค่

0.78

Only

0.75

 only

0.75

脚注の使い方

0.74

 Only

0.73

only

0.73

 Apenas

0.73

 pouze

0.72

Activations Density 0.251%

phrases that indicate conditions or limitations on actions or rights

No Comments

No Known Activations