INDEX

Explanations

terms that indicate a state of normalcy or typical physiological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ono

-0.44

extends

-0.42

 kvůli

-0.41

Hor

-0.40

ão

-0.40

empre

-0.39

 cung

-0.39

 huellas

-0.39

 kanton

-0.38

POSITIVE LOGITS

 remission

0.90

 normality

0.89

 undamaged

0.85

 normalcy

0.81

ToBounds

0.81

 healthy

0.81

 snippetHide

0.80

StatusOK

0.80

 unharmed

0.78

 normals

0.78

Activations Density 1.370%

terms that indicate a state of normalcy or typical physiological conditions

No Comments

No Known Activations