INDEX

Explanations

occurrences of terms related to entity generation or class definitions in programming contexts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

setDo

-0.62

BASEPATH

-0.55

 sjø

-0.53

CEAN

-0.52

isContained

-0.52

帖最后由

-0.52

็จ

-0.51

VERTIS

-0.51

purl

-0.50

MOUTH

-0.50

POSITIVE LOGITS

ens

0.82

 conjugate

0.75

abetes

0.71

ovsky

0.70

legate

0.65

enska

0.65

 iprot

0.64

 relegated

0.63

enser

0.63

ovsk

0.62

Activations Density 0.058%

occurrences of terms related to entity generation or class definitions in programming contexts

No Comments

No Known Activations