INDEX

Explanations

metadata or structured information related to documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

tagext

-0.67

 ſche

-0.60

 diſt

-0.57

 greateſt

-0.57

 uſe

-0.54

 apellidos

-0.53

 perſon

-0.53

 houſe

-0.52

 cauſe

-0.52

 Michaelis

-0.52

POSITIVE LOGITS

Autoritní

0.66

Aiheesta

0.62

Rüyada

0.60

 NSCoder

0.60

 StatelessWidget

0.59

tvguidetime

0.58

principalColumn

0.56

0.54

 AssemblyTitle

0.53

Activations Density 0.424%

metadata or structured information related to documents

No Comments

No Known Activations