INDEX

Explanations

references to academic publications and corresponding metrics

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

ására

-0.55

engar

-0.53

hdys

-0.52

JsonHelper

-0.51

tehen

-0.51

ivre

-0.49

WriteTagHelper

-0.49

ومه

-0.49

verzeichnis

-0.48

ivant

-0.48

POSITIVE LOGITS

 فريبيس

0.75

RenderAtEndOf

0.68

 ModelExpression

0.68

complexContent

0.67

 незавершена

0.63

 صوتيه

0.63

ScopeManager

0.56

 AttributeSet

0.56

IsContent

0.55

 Roskov

0.54

Activations Density 1.480%

references to academic publications and corresponding metrics

No Comments

No Known Activations