INDEX

Explanations

instances of the word "up" in various contexts

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

"Up"

np_acts-logits-general · gemini-2.0-flash

up to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

PerformLayout

-0.85

 itſelf

-0.78

VIAF

-0.76

 pleaſure

-0.75

 faſt

-0.75

 himſelf

-0.74

脚注の使い方

-0.73

 themſelves

-0.72

ſelves

-0.71

出版年

-0.71

POSITIVE LOGITS

Up

0.69

up

0.66

ups

0.61

 down

0.59

Up

0.58

EndContext

0.58

 front

0.53

 Down

0.53

Ups

0.53

Down

0.51

Activations Density 0.098%

instances of the word "up" in various contexts

"Up"

up to

No Comments

No Known Activations