INDEX

Explanations

technical instructions and code snippets related to software configuration

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Shakspeare

-0.57

 CORRECT

-0.54

 tena

-0.54

PreInfinity

-0.53

[](

-0.50

 corretto

-0.50

 Ensign

-0.49

rasında

-0.49

 Мексичка

-0.48

stood

-0.48

POSITIVE LOGITS

rungsseite

0.72

IndentedString

0.72

ThroughAttribute

0.65

 <<<<<<<<<<<<<<

0.65

 estimés

0.65

 nahilalakip

0.63

SharedCtor

0.62

MenuInflater

0.58

hyrchwyd

0.57

Tikang

0.55

Activations Density 1.062%

technical instructions and code snippets related to software configuration

No Comments

No Known Activations