INDEX

Explanations

unprocessed numerical or tabular data related to health statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.27.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

ſcher

-0.90

rungsseite

-0.88

 AssemblyCulture

-0.82

aarrggbb

-0.81

 PeEnEo

-0.80

 desmotivaciones

-0.80

migrationBuilder

-0.77

 feroit

-0.77

 سكانية

-0.77

Viited

-0.77

POSITIVE LOGITS

0.67

0.56

0.53

0.51

0.42

↵↵↵↵

0.41

0.40

↵↵

0.39

Activations Density 0.455%

unprocessed numerical or tabular data related to health statistics

No Comments

No Known Activations