INDEX

Explanations

relationships and connections between family members

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

Punctuation followed by other tokens

np_acts-logits-general · gemini-2.0-flash

.NET framework or code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

mybatisplus

-0.66

 חיצוניים

-0.61

mapStateToProps

-0.59

protoc

-0.57

Naissance

-0.54

 Paglinawan

-0.53

ManagedBean

-0.53

ésultat

-0.53

 marginBottom

-0.53

ership

-0.52

POSITIVE LOGITS

 Relatives

0.64

Visiting

0.58

aarrggbb

0.56

 Visiting

0.56

 فريبيس

0.54

 OMIT

0.52

 Calling

0.52

RenderAtEndOf

0.52

Calling

0.51

JSONException

0.51

Activations Density 0.078%

relationships and connections between family members

Punctuation followed by other tokens

.NET framework or code snippets

No Comments

No Known Activations