INDEX

Explanations

phrases indicating the significance of particular elements or concepts

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

 local

-0.48

local

-0.46

<bos>

-0.43

يمق

-0.43

 aliviar

-0.42

 nahilalakip

-0.42

 part

-0.41

 habituales

-0.41

 BoxFit

-0.41

isEnd

-0.41

POSITIVE LOGITS

#+#

0.85

ScopeManager

0.78

 saddest

0.76

anglès

0.75

Hentet

0.74

 proudest

0.73

 clearest

0.73

 greatest

0.71

testens

0.71

 poorest

0.71

Activations Density 0.124%

phrases indicating the significance of particular elements or concepts

No Comments

No Known Activations