INDEX

Explanations

terms associated with mental health symptoms and disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

脚注の使い方

-0.65

jago

-0.50

 rendel

-0.49

addClass

-0.48

InjectMocks

-0.48

deelte

-0.47

 stedet

-0.47

vantages

-0.47

LElement

-0.46

']).

-0.45

POSITIVE LOGITS

 immunity

0.92

 immune

0.91

 metabolism

0.90

 blood

0.85

 digestion

0.79

 circulation

0.79

 appetite

0.74

 eyesight

0.73

 respiration

0.72

 Immune

0.72

Activations Density 0.695%

terms associated with mental health symptoms and disorders

No Comments

No Known Activations