INDEX

Explanations

negative traits or behaviors of characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

MERCIAL

-0.60

 "$@"

-0.57

 stiefel

-0.56

ERICAN

-0.56

coccal

-0.56

ATUS

-0.55

Ǧ

-0.54

ICAGO

-0.54

ETHODS

-0.54

Quellen

-0.52

POSITIVE LOGITS

 typelib

0.69

HostException

0.64

 Normdatei

0.59

 ivelany

0.55

jsxFileName

0.55

 defaultstate

0.54

 AssemblyProduct

0.53

 الرياضيه

0.52

 Kirche

0.52

іга

0.51

Activations Density 1.446%

negative traits or behaviors of characters

No Comments

No Known Activations