INDEX

Explanations

references to specific names or identifiers in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ChildScrollView

-0.75

 محفوظة

-0.61

elemField

-0.59

SourceChecksum

-0.56

Society

-0.55

our

-0.52

ITARY

-0.52

 getopt

-0.52

人民共和国

-0.51

 Society

-0.50

POSITIVE LOGITS

BASEPATH

0.73

AnimationsModule

0.72

 Bambi

0.57

apnews

0.57

 ſtate

0.56

 purpoſe

0.55

 joaat

0.53

 ſta

0.53

 pleaſure

0.53

 fotografico

0.52

Activations Density 0.238%

references to specific names or identifiers in a technical context

No Comments

No Known Activations