INDEX

Explanations

terms related to error codes or statuses in technical 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

Negative Logits

 Pauly

-0.82

 Worthington

-0.75

portlet

-0.74

ن

-0.71

 Dorn

-0.71

 control

-0.68

LOTTE

-0.68

 Schmitt

-0.67

ddha

-0.67

 Champaign

-0.66

POSITIVE LOGITS

ET

1.11

et

1.09

CET

1.07

ET

1.06

Ket

0.98

Ket

0.88

dfunding

0.87

KET

0.83

ket

0.82

USET

0.81

Activations Density 0.035%

terms related to error codes or statuses in technical contexts

No Known Activations