INDEX

Explanations

references to evidence and supporting data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 RouterModule

-0.77

 useRouter

-0.76

ptonshire

-0.73

lidays

-0.71

Tembelea

-0.71

expandindo

-0.70

 كومونز

-0.70

ertale

-0.70

MigrationBuilder

-0.69

ỏa

-0.67

POSITIVE LOGITS

evidence

1.85

 evidence

1.83

 Evidence

1.80

 EVIDENCE

1.73

Evidence

1.73

 evidences

1.54

 Evid

1.44

 evidencia

1.16

vidence

1.14

 evid

1.13

Activations Density 0.138%

references to evidence and supporting data

No Comments

No Known Activations