INDEX

Explanations

mentions of the word "floor" and related references in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ⓧ

-0.81

../../

-0.69

 AssemblyCulture

-0.69

WriteAttribute

-0.67

eratops

-0.67

 continúas

-0.66

ViewFeatures

-0.66

schöne

-0.61

 esternos

-0.60

 Dink

-0.60

POSITIVE LOGITS

 floor

1.13

 floors

1.13

 Floor

1.06

 FLOOR

1.00

Floor

0.97

 flooring

0.94

 Floors

0.94

floor

0.93

 ground

0.87

FLOOR

0.87

Activations Density 0.132%

mentions of the word "floor" and related references in various contexts

No Comments

No Known Activations