INDEX

Explanations

references to an "agency"

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

rxjs

-0.79

ert

-0.72

 estimés

-0.70

 Steuer

-0.70

toPromise

-0.69

 CURLOPT

-0.69

 Wirt

-0.69

intre

-0.68

intr

-0.68

ard

-0.67

POSITIVE LOGITS

agencies

1.15

 Agencies

1.13

 agencies

1.10

Agencies

1.07

agency

0.97

 AGENCY

0.97

ViewFeatures

0.96

 Agency

0.95

Agency

0.94

 agency

0.91

Activations Density 0.006%

references to an "agency"

No Comments

No Known Activations