INDEX

Explanations

words commonly used in scientific publications, especially related to experimental methods and results.

oai_token-act-pair · gemini-2.0-flash

spherical objects

np_token-act-pair-logits · gpt-4o-mini

balls and spheres

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntentFilter

-0.60

存于互联网档案馆

-0.56

rizona

-0.55

gridy

-0.48

openConnection

-0.48

 planten

-0.46

 flapping

-0.46

RectangleBorder

-0.46

الإنجليزية

-0.46

ogonal

-0.45

POSITIVE LOGITS

 ball

0.84

balls

0.82

 balls

0.82

 spheres

0.78

 spherical

0.77

BALL

0.76

 BALL

0.74

 sphere

0.73

ball

0.69

 hard

0.69

Activations Density 4.405%

words commonly used in scientific publications, especially related to experimental methods and results.

spherical objects

balls and spheres

No Comments

No Known Activations