INDEX

Explanations

references to tearing or breaking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 kasarigan

-0.84

 дописавши

-0.72

 ModelExpression

-0.70

HasIndex

-0.65

WriteAttribute

-0.64

AccessorTable

-0.64

igshid

-0.59

aspectj

-0.56

DispatchToProps

-0.55

httphttps

-0.55

POSITIVE LOGITS

 apart

0.88

rip

0.82

 ripping

0.78

 tore

0.77

Rip

0.74

 tearing

0.73

 tear

0.72

 ripped

0.71

 torn

0.68

 Torn

0.68

Activations Density 0.114%

references to tearing or breaking

No Comments

No Known Activations