INDEX

Explanations

references to utilities in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 transférez

-0.96

 utafitiHapana

-0.91

VersionUID

-0.74

ConstraintMaker

-0.72

bukkit

-0.61

 rotors

-0.61

tagHelperRunner

-0.60

 onData

-0.59

 anest

-0.59

 DbType

-0.58

POSITIVE LOGITS

 utility

0.93

utility

0.82

Utility

0.81

Utilities

0.79

 Utility

0.77

utilities

0.75

']],

0.70

 utilities

0.70

'}>

0.65

?";

0.65

Activations Density 0.121%

references to utilities in various contexts

No Comments

No Known Activations