INDEX

Explanations

terms related to prescriptions and medication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

astify

-0.81

endregion

-0.74

 Seidel

-0.71

mmation

-0.71

 Selig

-0.69

 sevi

-0.69

 beschik

-0.68

 tapa

-0.68

 Sevilla

-0.67

vezető

-0.67

POSITIVE LOGITS

 pres

1.08

pres

1.07

 Ones

1.05

 ones

1.01

Ones

0.93

 Pres

0.86

Pres

0.83

 PRES

0.83

Coz

0.77

 Chwiliwch

0.75

Activations Density 0.113%

terms related to prescriptions and medication

No Comments

No Known Activations