INDEX

Explanations

locations, particularly geographic names and street names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Portail

-0.69

MemoryWarning

-0.66

脚注の使い方

-0.63

]};

-0.58

__((

-0.56

Skocz

-0.56

 propOrder

-0.56

новништво

-0.55

protoimpl

-0.54

 Normdatei

-0.54

POSITIVE LOGITS

 street

0.84

 Street

0.78

 streets

0.69

Street

0.66

street

0.66

 Streets

0.64

 STREET

0.62

streets

0.55

Streets

0.54

 Avenue

0.54

Activations Density 0.165%

locations, particularly geographic names and street names

No Comments

No Known Activations