INDEX

Explanations

references to voltage levels in electrical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 mapStateToProps

-0.78

 Darío

-0.74

 HasFactory

-0.73

ChildScrollView

-0.69

endpush

-0.64

 darted

-0.64

ContentLoaded

-0.63

theless

-0.62

ArgsConstructor

-0.62

mapStateToProps

-0.61

POSITIVE LOGITS

 packet

0.66

out

0.64

out

0.61

METHOD

0.58

 pick

0.55

OUT

0.55

 outs

0.54

 picks

0.53

 voltage

0.51

outs

0.51

Activations Density 0.132%

references to voltage levels in electrical contexts

No Comments

No Known Activations