INDEX

Explanations

structured data formats and coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

InjectAttribute

-1.30

GEBURTSDATUM

-0.98

 nakalista

-0.98

 propOrder

-0.97

 AssemblyCulture

-0.90

addCriterion

-0.90

 GenerationType

-0.89

rungsseite

-0.88

 doInBackground

-0.84

webElementXpaths

-0.83

POSITIVE LOGITS

[toxicity=0]

0.64

0.61

Ints

0.55

0.54

HasValue

0.53

 Ebene

0.51

RND

0.50

0.49

niti

0.49

 plans

0.48

Activations Density 0.127%

structured data formats and coding elements

No Comments

No Known Activations