INDEX

Explanations

tokens and identifiers associated with orders and identification numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

енча

-0.62

oa̍t

-0.60

fillna

-0.59

 ktorí

-0.58

Statistiche

-0.58

 gepubliceerd

-0.56

Portály

-0.55

󠁴

-0.53

 monotonous

-0.52

 mapStateToProps

-0.52

POSITIVE LOGITS

glGen

0.73

entyfik

0.57

 identifier

0.56

 uniquely

0.56

 numbering

0.56

LEncoder

0.55

 assigned

0.55

唯一

0.54

INSEE

0.54

Referanser

0.52

Activations Density 0.894%

tokens and identifiers associated with orders and identification numbers

No Comments

No Known Activations