INDEX

Explanations

expressions or symbols related to mathematical notation or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

LookAnd

-0.76

AndEndTag

-0.72

eeper

-0.66

TagHelpers

-0.62

ientôt

-0.56

தை

-0.55

iecie

-0.55

 समीक्षक

-0.55

CodeAttribute

-0.54

ArgsConstructor

-0.54

POSITIVE LOGITS

1.11

 للاسماء

0.88

ll

0.70

enumi

0.70

 يتيمه

0.67

osoba

0.65

 Deed

0.64

 informée

0.64

ls

0.62

 فريبيس

0.62

Activations Density 0.069%

expressions or symbols related to mathematical notation or structures

No Comments

No Known Activations