INDEX

Explanations

the beginning of a new document or significant section, indicated by specific formatting tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

WebElementEntity

-0.89

########.

-0.89

windowFixed

-0.88

Diwedd

-0.84



-0.83

 createSlice

-0.82

GEBURTSDATUM

-0.80

 uska

-0.80

TProtocol

-0.78

afficheront

-0.78

POSITIVE LOGITS

 Myself

0.74

IOUtils

0.74

myself

0.71

Myself

0.69

 myself

0.69

 throm

0.68

 selves

0.67

 ourselves

0.67

Nucl

0.67

 yourself

0.63

Activations Density 0.027%

the beginning of a new document or significant section, indicated by specific formatting tags

No Comments

No Known Activations