INDEX

Explanations

references to ongoing situations or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 ModelExpression

-0.85

RegistryLite

-0.85

LookAnd

-0.81

хьтан

-0.75

tahui

-0.74

felves

-0.74

 kasarigan

-0.72

elemField

-0.71

IndentedString

-0.71

rungsseite

-0.71

POSITIVE LOGITS

 still

0.78

 Still

0.77

Still

0.73

still

0.72

 malgré

0.69

 siguen

0.68

 weiterhin

0.68

 despite

0.62

 fortfarande

0.61

 STILL

0.60

Activations Density 0.358%

references to ongoing situations or states

No Comments

No Known Activations