INDEX

Explanations

summaries of experimental results and analyses

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

 disambiguazione

-0.63

脚注の使い方

-0.59

insics

-0.53

رشف

-0.52

ftagPool

-0.51

Zacks

-0.50

########.

-0.49

Nope

-0.47

+#+

-0.47

 lenker

-0.47

POSITIVE LOGITS

如下

0.78

 Table

0.69

如下图

0.69

Table

0.69

 table

0.67

 diagram

0.66

setVerticalGroup

0.63

IntoConstraints

0.63

 below

0.61

shown

0.60

Activations Density 0.231%

summaries of experimental results and analyses

No Comments

No Known Activations