INDEX

Explanations

references to axes or axis-related concepts in geometrical or rotational 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 وتسجيلات

-0.74

 Newberry

-0.73

ruptcy

-0.67

?");

-0.65

 Sopho

-0.64

 "));

-0.64

mater

-0.63

SP

-0.63

żym

-0.63

 dred

-0.63

POSITIVE LOGITS

 axis

1.68

 Axis

1.60

axis

1.57

 AXIS

1.49

Axis

1.42

 axes

1.38

AXIS

1.34

GetAxis

1.15

xis

1.14

轴

1.10

Activations Density 0.071%

references to axes or axis-related concepts in geometrical or rotational contexts

No Comments

No Known Activations