INDEX

Explanations

function or variable calls related to "current" or "cur" specifically indicating objects or state management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 rarement

-0.59

 récemment

-0.58

balleur

-0.56

so

-0.51

 furent

-0.50

وامل

-0.50

“

-0.49

 tewas

-0.48

 souvent

-0.48

 perlu

-0.47

POSITIVE LOGITS

ſelf

1.07

 Monfieur

1.02

 purpoſe

0.96

 iſt

0.95

 preſent

0.94

ſelves

0.94

 Jefus

0.92

 Anſ

0.91

 myſelf

0.91

 Majefty

0.90

Activations Density 0.338%

function or variable calls related to "current" or "cur" specifically indicating objects or state management

No Comments

No Known Activations