INDEX

Explanations

phrases indicating proximity or 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mugabe

-0.79

FIS

-0.72

Manbalar

-0.72

 MUSE

-0.72

 Schi

-0.71

 étage

-0.71

 Moors

-0.70

 cyst

-0.68

 Selig

-0.68

OSP

-0.68

POSITIVE LOGITS

 around

2.96

 Around

2.72

Around

2.71

around

2.69

 AROUND

2.56

AROUND

2.46

 autour

1.93

 alrededor

1.87

 rundt

1.78

 вокруг

1.63

Activations Density 0.039%

phrases indicating proximity or spatial context

No Comments

No Known Activations