INDEX

Explanations

references to different aspects or features of a subject matter

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

 Barrow

-0.87

 Frisch

-0.85

RSI

-0.81

 Rece

-0.80

 Darm

-0.77

emu

-0.77

ChildScrollView

-0.77

 Cardona

-0.77

chitis

-0.76

ctose

-0.76

POSITIVE LOGITS

 Aspects

0.93

 Aspect

0.92

Aspects

0.85

Aspect

0.83

 aspect

0.82

 ASPECTS

0.82

égard

0.81

 aspects

0.79

aspectj

0.79

 AssemblyVersion

0.72

Activations Density 0.074%

references to different aspects or features of a subject matter

No Comments

No Known Activations