INDEX

Explanations

references to time-related concepts

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

 дописавши

-0.67

]")]

-0.60

 otomatig

-0.58

 članak

-0.56

 kasarigan

-0.56

habad

-0.56

estinations

-0.56

(||

-0.55

 jScrollPane

-0.55

ielsen

-0.55

POSITIVE LOGITS

醐

0.64

 obviously

0.63

verständlich

0.61

 obvious

0.59

 moindre

0.58

 whatever

0.57

 natürlich

0.55

 maje

0.55

EndContext

0.55

 évidemment

0.54

Activations Density 0.348%

references to time-related concepts

No Comments

No Known Activations