INDEX

Explanations

evidence of validation or proof in various contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AspNetCore

-1.05

发表于

-0.99

 ModelExpression

-0.91

 خارجية

-0.90

 autorytatywna

-0.87

Controllo

-0.85

>{@

-0.81

 كومونز

-0.79

elemField

-0.77

lâ

-0.76

POSITIVE LOGITS

 proved

1.03

 Prove

1.02

 prove

1.00

Prove

0.95

 proves

0.92

prove

0.85

 Proven

0.83

 proving

0.82

 Prow

0.79

 Proving

0.76

Activations Density 0.028%

evidence of validation or proof in various contexts

No Comments

No Known Activations