INDEX

Explanations

names and relationships of family members

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Minneapolis

-0.67

liesslich

-0.61

pacific

-0.60

Minneapolis

-0.60

 pacific

-0.59

 ferdig

-0.58

neapolis

-0.58

 commerciales

-0.57

chicago

-0.57

Fcn

-0.56

POSITIVE LOGITS

 Alabama

0.66

 Tennessee

0.64

 Memphis

0.61

 yall

0.59

 okra

0.58

 pecans

0.57

 Bama

0.56

Tennessee

0.55

Alabama

0.55

Eub

0.55

Activations Density 0.511%

names and relationships of family members

No Comments

No Known Activations