INDEX

Explanations

code snippets involving random number generation and usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

solids

-0.41

 serangga

-0.41

žné

-0.38

de

-0.37

Requiem

-0.37

ulemon

-0.37

光明

-0.36

("}");

-0.36

…

-0.36

POLICY

-0.35

POSITIVE LOGITS

protoimpl

1.16

nextInt

1.06

 randint

1.03

 myſelf

1.01

 Theſe

0.99

randrange

0.98

 Diſ

0.96

 Majefty

0.95

 Houſe

0.95

 Reſ

0.94

Activations Density 0.056%

code snippets involving random number generation and usage

No Comments

No Known Activations