INDEX

Explanations

evidence of results or findings in scientific studies

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

 المعيارى

-0.80

 vägen

-0.58

SPATH

-0.58

 kyse

-0.58

 leſs

-0.57

 mesmos

-0.56

 avoient

-0.56

 magique

-0.56

 jäsen

-0.55

 Atmosphere

-0.55

POSITIVE LOGITS

WebElementEntity

0.77

gway

0.71

 demonstrated

0.66

 exhibited

0.62

 reportedly

0.61

 OMIT

0.60

 reported

0.59

)))));

0.58

có

0.58

 displays

0.58

Activations Density 0.883%

evidence of results or findings in scientific studies

No Comments

No Known Activations