INDEX

Explanations

references to user interface elements related to web documents and code formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 himo

-0.78

aarrggbb

-0.76

 propOrder

-0.72

enterOuterAlt

-0.65

TypedDataSet

-0.64

halb

-0.64

naire

-0.61

subplots

-0.61

 Majefty

-0.61

writeFieldEnd

-0.57

POSITIVE LOGITS

 مشين

0.64

 Roskov

0.62

__*/

0.61

 saites

0.60

 cérami

0.58

</i>

0.58

</em>

0.53

=*/

0.53

 ChromeDriver

0.53

findpost

0.52

Activations Density 0.288%

references to user interface elements related to web documents and code formatting

No Comments

No Known Activations