INDEX

Explanations

repeated mentions of a specific individual, specifically Wilson

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

枚

-0.55

MD

-0.52

ագ

-0.49

 opts

-0.48

dtd

-0.48

od

-0.48

 yere

-0.48

arda

-0.47

 Kabir

-0.47

 beri

-0.47

POSITIVE LOGITS

 Wilson

0.92

SerializedSize

0.89

 lung

0.86

 coal

0.85

Wilson

0.81

 Coal

0.78

 wilson

0.77

 WILSON

0.77

 فريبيس

0.75

 Roskov

0.74

Activations Density 0.079%

repeated mentions of a specific individual, specifically Wilson

No Comments

No Known Activations