INDEX

Explanations

references to counting or numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

digm

-0.72

UpInside

-0.69

 indisponible

-0.62

 Helms

-0.56

argest

-0.56

nologies

-0.55

ußer

-0.55

didSet

-0.53

 umum

-0.53

igenschaften

-0.53

POSITIVE LOGITS

 counting

1.85

 counted

1.82

 Counting

1.73

Counting

1.70

counting

1.59

 counts

1.58

 COUNT

1.47

counted

1.45

 count

1.44

 Counts

1.37

Activations Density 0.250%

references to counting or numerical values

No Comments

No Known Activations