INDEX

Explanations

terms related to science and research methodologies

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

she

-0.51

RegressionTest

-0.43

...

-0.42

 gere

-0.41

xc

-0.41

 calldata

-0.41

Ro

-0.40

Dr

-0.40

শে

-0.39

 Fuchs

-0.39

POSITIVE LOGITS

DockStyle

1.00

 himſelf

0.99

 myſelf

0.97

 itſelf

0.95

 houſe

0.92

 preſent

0.91

 purpoſe

0.89

 themſelves

0.88

 Houſe

0.88

 ſtate

0.85

Activations Density 1.469%

terms related to science and research methodologies

No Comments

No Known Activations