INDEX

Explanations

phrases that indicate conditions, events, or changes in status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

migrationBuilder

-0.71

tênis

-0.57

SetOutput

-0.56

LLocation

-0.56

 ་་

-0.53

acamata

-0.53

clusal

-0.53

 Fordham

-0.53

TestBed

-0.52

 vectorielles

-0.51

POSITIVE LOGITS

StoryboardSegue

0.72

aarrggbb

0.63

="#"><

0.60

 resourceCulture

0.58

 Paglinawan

0.57

delwed

0.56

Gemeinden

0.56

Carriera

0.55

 Roskov

0.55

 AssemblyCulture

0.54

Activations Density 1.765%

phrases that indicate conditions, events, or changes in status

No Comments

No Known Activations