INDEX

Explanations

specific metrics or standards used to evaluate or describe quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

CWE

-0.61

gnore

-0.57

 Nicosia

-0.54

 Covent

-0.54

μάτων

-0.53

новништво

-0.53

 Planeta

-0.53

daq

-0.53

 raiſ

-0.52

 Albu

-0.52

POSITIVE LOGITS

 nahilalakip

0.71

TestFixture

0.64

Considering

0.63

 considering

0.60

considering

0.59

 autorytatywna

0.58

 Considering

0.57

 Verhältnisse

0.57

VersionUID

0.56

sizeCache

0.55

Activations Density 0.119%

specific metrics or standards used to evaluate or describe quality

No Comments

No Known Activations