INDEX

Explanations

terms related to "view" or visibility

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

Tokens appearing after "view"

np_acts-logits-general · gemini-2.0-flash

view pager, viewpoints, view hierarchy

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

 bezeichneter

-0.73

期刊论文

-0.67

DialogContent

-0.64

XmlAccessorType

-0.64

Anhalt

-0.64

amoja

-0.61

damente

-0.60

kowym

-0.58

AccessFile

-0.56

struzioni

-0.56

POSITIVE LOGITS

ership

0.97

finder

0.77

tiful

0.73

sidemargin

0.68

 AspNetCore

0.67

points

0.66

point

0.64

CppCodeGen

0.62

ัฒนา

0.61

 disambiguazione

0.60

Activations Density 0.097%

terms related to "view" or visibility

Tokens appearing after "view"

view pager, viewpoints, view hierarchy

No Comments

No Known Activations