INDEX

Explanations

descriptions of buildings and their features

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

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

出版年

-0.67

 Litt

-0.59

tifact

-0.58

Zij

-0.57

tley

-0.54

 Shaksp

-0.53

BIÉN

-0.53

complexContent

-0.53

IGraphics

-0.53

enosine

-0.52

POSITIVE LOGITS

 spacious

0.83

 living

0.81

 rooms

0.79

 open

0.77

 master

0.74

 bedrooms

0.74

rooms

0.69

 kitchens

0.69

 kitchen

0.68

 Spacious

0.67

Activations Density 0.046%

descriptions of buildings and their features

No Comments

No Known Activations