INDEX

Explanations

references to different hierarchical levels or scales in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

STE

-0.55

>{"

-0.51

arischen

-0.50

Media

-0.50

Nen

-0.50

)));

-0.49

 ziehen

-0.49

wicz

-0.49

şiv

-0.48

NameInMap

-0.48

POSITIVE LOGITS

 level

0.85

 úrov

0.72

 LEVEL

0.71

GenerationType

0.69

level

0.67

 individual

0.67

niveau

0.67

 уровне

0.66

InitVars

0.64

nivå

0.64

Activations Density 0.311%

references to different hierarchical levels or scales in various contexts

No Comments

No Known Activations