INDEX

Explanations

references to prior discussions or descriptions within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

########.

-0.84

LookAnd

-0.81

contentLoaded

-0.70

 للاسماء

-0.69

 Signalez

-0.65

发表于

-0.64

 jScrollPane

-0.59

 kuin

-0.56

saraba

-0.53

CloseOperation

-0.53

POSITIVE LOGITS

 earlier

0.96

 elsewhere

0.94

 previously

0.80

 above

0.78

 somewhere

0.72

earlier

0.71

 below

0.70

ไว้

0.70

previously

0.65

 later

0.65

Activations Density 0.548%

references to prior discussions or descriptions within the text

No Comments

No Known Activations