INDEX

Explanations

technical terms and identifiers related to scientific and computational contexts

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

 sequelize

-0.66

-0.61

Зноскі

-0.59

capital

-0.55

 capital

-0.53

לה

-0.51

నా

-0.50

 each

-0.50

Fre

-0.50

POSITIVE LOGITS

 greateſt

0.93

 pleaſure

0.81

 itſelf

0.81

balleur

0.80

 beſt

0.79

 houſe

0.77

 Hift

0.76

 Conſ

0.75

 himſelf

0.75

 themſelves

0.75

Activations Density 0.444%

technical terms and identifiers related to scientific and computational contexts

No Comments

No Known Activations