INDEX

Explanations

terms related to recovery and rehabilitation

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

"recovery" or a variation of it

np_acts-logits-general · gemini-2.0-flash

recovery

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.68

 تانيه

-0.67

 nonatomic

-0.67

 CreateTagHelper

-0.64

isContained

-0.61

DebuggerStep

-0.61

createStatement

-0.60

setOnItem

-0.59

DotNetBar

-0.59

 kasarigan

-0.58

POSITIVE LOGITS

 Recover

1.02

 recoveries

1.00

 recover

0.95

Recover

0.92

 recovery

0.90

 Recovery

0.86

Recovery

0.86

recover

0.83

Recuper

0.82

recovery

0.81

Activations Density 0.145%

terms related to recovery and rehabilitation

"recovery" or a variation of it

recovery

No Comments

No Known Activations