INDEX

Explanations

elements related to document structure and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Kanpo

-0.54

Hochspringen

-0.53

kswagen

-0.50

 gemeenten

-0.47

itatis

-0.45

umą

-0.44

fsen

-0.43

izeit

-0.43

Revenir

-0.43

כשיו

-0.43

POSITIVE LOGITS

Datuak

0.66

曖昧さ回避

0.61

 Vikipedi

0.61

SourceChecksum

0.58

InvalidProtocol

0.58

contentLoaded

0.58

 appelez

0.57

MarshalTo

0.57

onAttach

0.56

WireFormatLite

0.56

Activations Density 0.055%

elements related to document structure and formatting

No Comments

No Known Activations