INDEX

Explanations

instances of counting or enumeration

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

 indisponible

-0.68

digm

-0.62

intenant

-0.62

Higgins

-0.58

hadiran

-0.58

UpInside

-0.57

原始内容存档于

-0.57

tujuan

-0.56

ViewSet

-0.56

 BorderRadius

-0.56

POSITIVE LOGITS

 counting

1.93

 counted

1.92

 Counting

1.86

Counting

1.72

counting

1.72

 counts

1.72

 COUNT

1.60

 count

1.56

 Counts

1.55

counted

1.53

Activations Density 0.105%

instances of counting or enumeration

No Comments

No Known Activations