INDEX

Explanations

the word "change" in contexts related to processes or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 empre

-0.57

akam

-0.53

sao

-0.52

him

-0.51

)))));

-0.50

que

-0.49

DO

-0.48

quia

-0.48

 mümkün

-0.48

ICOL

-0.48

POSITIVE LOGITS

URLException

0.95

 AssemblyCompany

0.94

principalColumn

0.91

 beginnetje

0.89

AnchorTagHelper

0.83

 snippetHide

0.83

Хьажоргаш

0.81

CloseOperation

0.79

SBATCH

0.79

LEncoder

0.78

Activations Density 0.372%

the word "change" in contexts related to processes or conditions

No Comments

No Known Activations