INDEX

Explanations

terms related to validity and acceptable formats

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

expandindo

-1.03

 springfox

-0.83

">//

-0.80

MigrationBuilder

-0.76

 Leto

-0.70

DSC

-0.70

….”

-0.70

 ComVisible

-0.69

TypedDataSet

-0.69

metto

-0.69

POSITIVE LOGITS

 valid

1.86

Valid

1.66

valid

1.65

 Valid

1.56

VALID

1.51

 VALID

1.43

 válida

1.34

 invalid

1.30

 isValid

1.29

isValid

1.26

Activations Density 0.054%

terms related to validity and acceptable formats

No Comments

No Known Activations