INDEX

Explanations

locations and references to London

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

•Steering evals

london

No Comments

Negative Logits



-0.93

posedge

-0.61

 VIAF

-0.59

 Waray

-0.57

 Aloha

-0.56

MemoryWarning

-0.56

 Middletown

-0.54

 Spokane

-0.54

 Normdatei

-0.54

onActivityResult

-0.53

POSITIVE LOGITS

 London

1.06

London

0.91

 Hammers

0.84

 Tube

0.84

 tube

0.84

 london

0.83

 Londres

0.83

 Southwark

0.81

Tube

0.81

london

0.79

Activations Density 0.234%

locations and references to London

No Comments

No Known Activations

locations and references to London

No Comments

No Known Activations