INDEX

Explanations

indicators of data structure or organization

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

RegressionTest

-0.66

ParallelGroup

-0.60

Rhestr

-0.59

 通販

-0.55

enderror

-0.54

หวัด

-0.54

LookAnd

-0.52

EndProject

-0.50

Cllr

-0.50

POSITIVE LOGITS

 ſche

0.82

 houſe

0.82

 Anſ

0.79

 Reſ

0.78

 ſch

0.77

 ſta

0.77

 iſt

0.76

 Jefus

0.76

expandindo

0.75

 Inſ

0.74

Activations Density 0.003%

indicators of data structure or organization

No Comments

No Known Activations