INDEX

Explanations

words related to academic and scientific terminology

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

Tokens before words ending in "en"

np_acts-logits-general · gemini-2.0-flash

word endings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ActionCreators

-0.80

 CreateTagHelper

-0.74

 AssemblyCulture

-0.70

 BoxFit

-0.70

DataAnnotations

-0.70

mapStateToProps

-0.69

NamedQuery

-0.67

PropertyChanging

-0.66

 Infórmanos

-0.66

Données

-0.65

POSITIVE LOGITS

ning

0.70

ek

0.67

eden

0.62

ized

0.60

thin

0.57

ellen

0.57

en

0.56

eken

0.56

ians

0.55

aken

0.53

Activations Density 0.390%

words related to academic and scientific terminology

Tokens before words ending in "en"

word endings

No Comments

No Known Activations