INDEX

Explanations

references to medical professionals or doctors

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lended

-0.83

hline

-0.76

 negó

-0.76

躇

-0.72

jfree

-0.72

 hinweg

-0.71

 Unidas

-0.70

NPD

-0.70

clientY

-0.69

thwaite

-0.64

POSITIVE LOGITS

 doctor

1.76

 Doctor

1.71

doctor

1.71

 doctors

1.67

Doctor

1.65

 DOCTOR

1.65

 Doctors

1.64

Doctors

1.54

doctors

1.50

DOCTOR

1.39

Activations Density 0.030%

references to medical professionals or doctors

No Comments

No Known Activations