INDEX

Explanations

references to memory and related concepts

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

 ویکی‌پدی

-0.80

wixt

-0.79

ⓧ

-0.76

 hvem

-0.76

 azeite

-0.76

ixante

-0.76

jectures

-0.76

 fleste

-0.76

 Giappone

-0.75

 antaranya

-0.74

POSITIVE LOGITS

 memory

2.42

 Memory

2.20

memory

2.09

 MEMORY

2.04

 memories

2.01

Memory

2.00

 Memories

1.87

MEMORY

1.77

Memories

1.73

 memoria

1.58

Activations Density 0.056%

references to memory and related concepts

No Comments

No Known Activations