INDEX

Explanations

terms associated with adaptation and self-concept changes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-0.67

cassandra

-0.63

 Pinterest

-0.52

Vanguard

-0.52

 تانيه

-0.51

 doInBackground

-0.51

vő

-0.50

 Kain

-0.49

pino

-0.49

Genesis

-0.48

POSITIVE LOGITS

webElementXpaths

0.91

 adapting

0.82

 accustomed

0.78

 accepting

0.77

 acceptance

0.75

 Theſe

0.74

 adjusting

0.73

适应

0.72

adaptation

0.72

 adjustment

0.72

Activations Density 0.228%

terms associated with adaptation and self-concept changes

No Comments

No Known Activations