INDEX

Explanations

terms related to medical diagnoses and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 للمعارف

-0.67

Chham

-0.66

<bos>

-0.61

owaną

-0.59

Przypisy

-0.59

}{*}{}

-0.59

elif

-0.57

owanej

-0.57

anthes

-0.55

tyimages

-0.54

POSITIVE LOGITS

 several

2.10

several

1.89

 many

1.80

 numerous

1.67

Several

1.64

 Several

1.57

 plusieurs

1.49

 varios

1.49

many

1.48

 vários

1.45

Activations Density 0.757%

terms related to medical diagnoses and evaluations

No Comments

No Known Activations