INDEX

Explanations

concepts and terminology related to scientific theories and models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 shame

-0.48

extAlignment

-0.45

CWE

-0.45

BASELINE

-0.45

 IOError

-0.44

廂

-0.43

Origine

-0.43

 Shame

-0.42

shame

-0.42

Билгалдахарш

-0.41

POSITIVE LOGITS

 requires

2.80

 require

2.70

 Requires

2.48

 requiring

2.35

requires

2.35

 Require

2.27

require

2.25

Requires

2.21

 requiere

2.04

 REQU

2.00

Activations Density 0.927%

concepts and terminology related to scientific theories and models

No Comments

No Known Activations