INDEX

Explanations

phrases related to location and spatial context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

roën

-0.81

 AssemblyCulture

-0.79

 Mojo

-0.76

 étage

-0.74

('|

-0.73

Mojo

-0.73

FIS

-0.73

 Mugabe

-0.72

CGI

-0.71

OSP

-0.69

POSITIVE LOGITS

 around

2.60

 Around

2.44

Around

2.42

around

2.37

 AROUND

2.27

AROUND

2.23

 autour

1.64

 alrededor

1.62

 rundt

1.55

 omkring

1.51

Activations Density 0.053%

phrases related to location and spatial context

No Comments

No Known Activations