INDEX

Explanations

references to specific cases or instances in a structured context

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

 Monfieur

-0.97

 Mercurio

-0.96

 raiſ

-0.93

 uſed

-0.93

 pleaſure

-0.91

 Theſe

-0.89

Память

-0.88

edicated

-0.85

 havaianas

-0.83

 bershka

-0.83

POSITIVE LOGITS

 cases

1.86

 case

1.73

 Cases

1.72

case

1.66

 Case

1.66

cases

1.60

Cases

1.59

 CASE

1.58

CASE

1.55

Case

1.52

Activations Density 0.697%

references to specific cases or instances in a structured context

No Comments

No Known Activations