INDEX

Explanations

references to categorization or grouping within a larger context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Morte

-0.41

Ál

-0.41

liquid

-0.40

hdc

-0.38

DC

-0.38

reality

-0.37

 visualisation

-0.37

 Staat

-0.36

Carne

-0.36

 Liquid

-0.35

POSITIVE LOGITS

 among

1.59

among

1.46

 AMONG

1.45

 Among

1.38

Among

1.35

 amongst

1.23

 parmi

1.18

 Amongst

1.15

 wśród

1.12

 среди

1.09

Activations Density 0.111%

references to categorization or grouping within a larger context

No Comments

No Known Activations