INDEX

Explanations

references to medical examinations and conditions

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

Medical tests and investigations

np_acts-logits-general · gemini-2.0-flash

medical tests and investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 BoxFit

-0.82

tvguidetime

-0.78

 GenerationType

-0.61

 насељу

-0.58

انيف

-0.57

PYX

-0.57

phorbia

-0.56

MethodManager

-0.55

ifrance

-0.54

Preheat

-0.53

POSITIVE LOGITS

 tests

1.19

 laboratory

1.04

 test

1.01

lab

0.99

 Tests

0.96

Tests

0.95

 labs

0.94

 laboratorio

0.91

 examination

0.91

 Laboratory

0.90

Activations Density 0.592%

references to medical examinations and conditions

Medical tests and investigations

medical tests and investigations

No Comments

No Known Activations