INDEX

Explanations

references to health issues or illnesses

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

 Schae

-0.68

 Wallace

-0.67

IgE

-0.67

 Farley

-0.67

coni

-0.67

Noel

-0.66

 الق

-0.66

ImageBackground

-0.65

WEBPACK

-0.65

Proced

-0.64

POSITIVE LOGITS

ill

1.16

ILL

1.14

ll

1.08

ILL

1.08

ill

1.05

 Till

1.02

Ill

1.00

Till

0.94

LL

0.94

Ill

0.94

Activations Density 0.088%

references to health issues or illnesses

No Comments

No Known Activations