INDEX

Explanations

references to "per" or variations of it, often associated with measurements or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AssemblyCulture

-0.69

usehen

-0.60

HasBeenSet

-0.59

 onCreateView

-0.57

 chinoise

-0.56

 onCancelled

-0.56

 infine

-0.56

GOTREF

-0.56

VolleyError

-0.55

iyle

-0.54

POSITIVE LOGITS

per

0.96

PER

0.95

Per

0.93

per

0.78

Per

0.77

 lenker

0.76

PER

0.76

 auto

0.70

peria

0.66

 perp

0.65

Activations Density 2.531%

references to "per" or variations of it, often associated with measurements or evaluations

No Comments

No Known Activations