INDEX

Explanations

terms related to medical research and treatment efficacy

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MigrationBuilder

-0.49

jär

-0.46

lasi

-0.45

 esternos

-0.45

vember

-0.45

antoms

-0.44

usermodel

-0.43

ifest

-0.43

IMPORTED

-0.43

ipan

-0.40

POSITIVE LOGITS

 treatment

2.17

 treatments

2.00

treatment

1.92

 Treatment

1.86

Treatment

1.80

 Treatments

1.74

 TREATMENT

1.74

 tratamiento

1.63

 therapy

1.63

treat

1.60

Activations Density 1.554%

terms related to medical research and treatment efficacy

No Comments

No Known Activations