INDEX

Explanations

references to uncertainty or questions about understanding

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

 CreateTagHelper

-0.77

 betweenstory

-0.74

IntoConstraints

-0.64

Cordialement

-0.61

+#+#

-0.60

Autoritní

-0.58

 ModelRenderer

-0.57

damento

-0.57

MessageOf

-0.57

webElementXpaths

-0.56

POSITIVE LOGITS

Basically

0.45

 advance

0.44

 Basically

0.44

 gracia

0.43

REST

0.43

rest

0.42

abat

0.42

oue

0.40

ue

0.40

 rowspan

0.40

Activations Density 0.203%

references to uncertainty or questions about understanding

No Comments

No Known Activations

references to uncertainty or questions about understanding

No Comments

No Known Activations