INDEX

Explanations

references to holes in technical descriptions or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 للمعارف

-0.85

SharedCtor

-0.82

بوابة

-0.77

 كومونز

-0.76

 ivelany

-0.74

لينكات

-0.72

UnsafeEnabled

-0.72

PreferredItem

-0.70

íncia

-0.69

tvguidetime

-0.67

POSITIVE LOGITS

 Hole

0.72

Hole

0.68

 Holes

0.64

hole

0.64

 HOLE

0.61

holes

0.58

 thermocouple

0.56

Phi

0.55

Fon

0.55

Cert

0.55

Activations Density 0.189%

references to holes in technical descriptions or specifications

No Comments

No Known Activations