INDEX

Explanations

references to experimental results or outcomes

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

 للاسماء

-0.74

aarrggbb

-0.73

verifyException

-0.72

 treo

-0.64

 Lyra

-0.64

rrggbb

-0.64

 demurrer

-0.62

RTGC

-0.61

)$/,

-0.61

 Coder

-0.58

POSITIVE LOGITS

 results

2.21

results

2.12

 Results

1.94

Results

1.92

 RESULTS

1.73

RESULTS

1.68

 resultados

1.34

 résultats

1.32

 Ergebnisse

1.24

 resultaten

1.17

Activations Density 0.147%

references to experimental results or outcomes

No Comments

No Known Activations