INDEX

Explanations

terms related to mathematical constraints and bounds in proofs or theorems

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

SourceChecksum

-0.84

@"/

-0.81

 nahilalakip

-0.81

 незавершена

-0.78

 AssemblyProduct

-0.78

 فريبيس

-0.77

 jScrollPane

-0.76

GraphicsUnit

-0.75

+#+#

-0.74

onOptions

-0.73

POSITIVE LOGITS

 bounds

1.01

 Bound

0.98

 bound

0.93

bounds

0.92

 Bounds

0.85

bound

0.84

Bound

0.82

BOUND

0.77

bounded

0.76

Bounds

0.75

Activations Density 0.042%

terms related to mathematical constraints and bounds in proofs or theorems

No Comments

No Known Activations