INDEX

Explanations

words related to strikes and physical confrontations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

NewUrlParser

-0.85

 Sagan

-0.84

escens

-0.83

HasAnnotation

-0.77

Elvis

-0.75

робнее

-0.74

enapa

-0.74

engkapnya

-0.73

phorbia

-0.72

 carpeta

-0.72

POSITIVE LOGITS

 strike

1.98

 Strike

1.93

 Strikes

1.89

 strikes

1.88

Strike

1.85

strike

1.79

 striking

1.58

 struck

1.46

Stri

1.39

stri

1.39

Activations Density 0.122%

words related to strikes and physical confrontations

No Comments

No Known Activations