INDEX

Explanations

occurrences of numeric values and object identifiers

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

AnchorTagHelper

-0.50

LEGGI

-0.46

ngdoc

-0.44

uken

-0.42

 Moss

-0.42

 peme

-0.41

 ProtoMessage

-0.41

 menudo

-0.40

KURZBESCHREIBUNG

-0.40

gehalt

-0.40

POSITIVE LOGITS

Personendaten

0.72

 resourceCulture

0.71

 المعيارى

0.67

########.

0.65

 ExecuteAsync

0.59

[]:

0.58

tvguidetime

0.58

CloseOperation

0.55

 onCancelled

0.54

webElementXpaths

0.53

Activations Density 0.121%

occurrences of numeric values and object identifiers

No Comments

No Known Activations