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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Laredo

-0.96

<sub>

-0.77

//

-0.76

owulf

-0.76

 Firefly

-0.76

{{{

-0.75

 Provid

-0.74

 Perla

-0.72

ledad

-0.72

mathcal

-0.71

POSITIVE LOGITS

Valley

0.83

 Valley

0.81

 Roost

0.79

Cym

0.76

WireFormatLite

0.75

Diz

0.74

 Cava

0.72

SV

0.71

interopRequire

0.71

trums

0.70

Activations Density 3.743%

proper nouns, specifically names of people and places

No Comments

No Known Activations