INDEX

Explanations

terms related to deprecation and activation status in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

########.

-0.60

ISupport

-0.53

#+#

-0.48

IsContent

-0.47

 TextAppearance

-0.44

PYX

-0.43

TypedDataSet

-0.42

pexpr

-0.42

 ***!

-0.41

‚¬

-0.41

POSITIVE LOGITS

 unused

0.85

 inactive

0.82

 Inactive

0.81

 deactivated

0.79

unused

0.78

 Unused

0.77

Unused

0.74

 Deprecated

0.72

Deprecated

0.72

 decommission

0.72

Activations Density 0.529%

terms related to deprecation and activation status in technical contexts

No Comments

No Known Activations