INDEX

Explanations

terms related to recovery and rehabilitation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

JvmStatic

-0.73

tzmann

-0.69

isDirectory

-0.67

InjectMocks

-0.67

tag

-0.65

jsxFileName

-0.62

npmjs

-0.62

verwijspagina

-0.61

 Kast

-0.60

Kast

-0.59

POSITIVE LOGITS

 Recover

1.57

 recoveries

1.51

 Recovery

1.41

 recovery

1.34

 RECOVERY

1.33

 recover

1.31

Recovery

1.29

 recoverable

1.24

 recovers

1.21

 recovered

1.20

Activations Density 0.080%

terms related to recovery and rehabilitation processes

No Comments

No Known Activations