INDEX

Explanations

references to processes and procedures

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

"process"

np_acts-logits-general · gemini-2.0-flash

process and its associated steps

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ArgsConstructor

-0.81

 himſelf

-0.79

 purpoſe

-0.78

Efq

-0.75

 Himo

-0.73

 Pública

-0.72

+#+#

-0.69

 HasFactory

-0.69

 Brute

-0.69

 faſt

-0.68

POSITIVE LOGITS

 processes

0.75

 Processes

0.65

Processes

0.64

PROCESS

0.61

ess

0.58

processes

0.58

 Process

0.57

 PROCESS

0.57

ual

0.56

 process

0.54

Activations Density 0.222%

references to processes and procedures

"process"

process and its associated steps

No Comments

No Known Activations