INDEX

Explanations

elements related to medical professions and practices

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

WithFormat

-0.54

\{\\

-0.54

Class

-0.52

databind

-0.51

וויק

-0.49

 betweenstory

-0.47

igans

-0.45

stat

-0.45

AccessorTable

-0.44

OLIC

-0.44

POSITIVE LOGITS

Dr

3.89

Dr

3.63

dr

3.05

dr

2.66

Drs

2.19

DR

2.02

 Doctor

2.01

 doctor

1.94

دکتر

1.84

DR

1.81

Activations Density 0.178%

elements related to medical professions and practices

No Comments

No Known Activations

elements related to medical professions and practices

No Comments

No Known Activations