INDEX

Explanations

technical elements and programming-related constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.56

-0.53

-0.49

-0.48

non

-0.48

ordnung

-0.45

 world

-0.45

USA

-0.45

-0.44

ìm

-0.44

POSITIVE LOGITS

 Савезне

0.95

sizeCache

0.94

脚注の使い方

0.92

ScopeManager

0.90

 snippetHide

0.89

Hochspringen

0.89

Życiorys

0.84

Personendaten

0.82

 tartalomajánló

0.82

Activations Density 0.441%

technical elements and programming-related constructs

No Comments

No Known Activations