INDEX

Explanations

proper nouns, specifically names of people and places

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Guzmán

-0.78

••

-0.75

 Guzman

-0.74

andExpect

-0.73

••••

-0.72

+#+#

-0.71

chartInstance

-0.71

Martina

-0.71

 Aditya

-0.70

 Raffa

-0.70

POSITIVE LOGITS

 Collins

0.87

Collins

0.86

 Cain

0.75

="{{$

0.75

 madison

0.73

Rüyada

0.73

 Chid

0.73

 Shalom

0.71

 Madison

0.69

 Gris

0.69

Activations Density 0.811%

proper nouns, specifically names of people and places

No Comments

No Known Activations