INDEX

Explanations

references to structured data or identifiers in technical contexts

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

adpleegd

-0.75

 lenker

-0.75

IVEREF

-0.63

ParallelGroup

-0.62

ServletException

-0.60

 OnTrigger

-0.58

ftagPool

-0.58

argate

-0.55

}],

-0.55

OrBuilder

-0.54

POSITIVE LOGITS

 leaderboard

0.77

 achievement

0.67

 competi

0.61

 bragging

0.60

 competition

0.58

 challenge

0.57

 achievements

0.57

 Achievement

0.56

 accomplishment

0.55

 Wettbewerb

0.54

Activations Density 0.366%

references to structured data or identifiers in technical contexts

No Comments

No Known Activations