INDEX

Explanations

instances of the word "often" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ſche

-0.56

IntoConstraints

-0.56

ſelf

-0.54

IContainer

-0.54

 cytok

-0.53

NM

-0.52

 Chriftian

-0.50

 isole

-0.48

balleur

-0.48

 mView

-0.48

POSITIVE LOGITS

 often

0.96

often

0.93

Often

0.91

 Often

0.86

 sometimes

0.79

 oftentimes

0.79

 frequently

0.78

Sometimes

0.77

 suele

0.77

 často

0.75

Activations Density 0.210%

instances of the word "often" in various contexts

No Comments

No Known Activations