INDEX

Explanations

code-like syntax and structure, indicating function definitions and variable manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Begriffsklä

-0.67

GOTREF

-0.66

 محفوظة

-0.66

 AttributeSet

-0.65

haden

-0.64

érature

-0.64

 snippetHide

-0.60

 ujednoznacz

-0.60

visits

-0.60

ownika

-0.59

POSITIVE LOGITS

 '\\;'

0.46

gcm

0.42

zuführen

0.40

/*++

0.40

 generales

0.40

cinfo

0.40

 onOptions

0.39

 irré

0.39

 frattempo

0.39

stddef

0.39

Activations Density 0.584%

code-like syntax and structure, indicating function definitions and variable manipulations

No Comments

No Known Activations