INDEX

Explanations

terms related to severity and adverse health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

躇

-0.76

HomeAsUp

-0.70

WithIOException

-0.70

roxene

-0.70

ഷ

-0.70

sí

-0.69

grana

-0.68

 Guel

-0.67

anz

-0.66

Qubit

-0.66

POSITIVE LOGITS

 Severe

1.82

 severe

1.80

Severe

1.75

severe

1.69

 severity

1.48

SEVERE

1.44

 sever

1.41

 fevere

1.39

 SEVER

1.38

 severely

1.38

Activations Density 0.160%

terms related to severity and adverse health conditions

No Comments

No Known Activations