INDEX

Explanations

terms related to medical conditions and their management

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

ending in "-ity" or "-ity" sounds

np_acts-logits-general · gemini-2.0-flash

gravity, majority, security, activity, efficacy

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ings

-0.89

ness

-0.86

est

-0.80

ations

-0.79

️

-0.77

}{*}{

-0.74

NESS

-0.74

ening

-0.70

nesses

-0.67

 otomatig

-0.67

POSITIVE LOGITS

yyy

0.88

yyyy

0.85

0.77

ます

0.70

yyyyy

0.69

ً

0.65

eis

0.64

Prensa

0.64

Sinopsis

0.64

ますね

0.63

Activations Density 0.880%

terms related to medical conditions and their management

ending in "-ity" or "-ity" sounds

gravity, majority, security, activity, efficacy

No Comments

No Known Activations