INDEX

Explanations

terms related to limiting, conflicting, or stabilizing effects in various contexts

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

that modify nouns

np_acts-logits-general · gemini-2.0-flash

influencing actions and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/******/

-0.63

 uovo

-0.60

 AssemblyCulture

-0.55

 Baillargeon

-0.54

 Administrativna

-0.52

出版年

-0.49

bootstrapcdn

-0.49

 Wiktionnaire

-0.49

__(/*!

-0.46

homonymie

-0.46

POSITIVE LOGITS

 factor

0.94

ingly

0.89

 factors

0.81

 effect

0.74

factor

0.74

factors

0.71

ValueStyle

0.69

ly

0.69

 agents

0.69

 force

0.68

Activations Density 0.321%

terms related to limiting, conflicting, or stabilizing effects in various contexts

that modify nouns

influencing actions and outcomes

No Comments

No Known Activations