INDEX

Explanations

numerical data and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

tvguidetime

-0.60

verwijspagina

-0.59

 cherchés

-0.50

<bos>

-0.47

mış

-0.44

 sought

-0.44

djangoproject

-0.44

 Exactos

-0.43

 cố

-0.43

Cyfeiriadau

-0.43

POSITIVE LOGITS

iastes

0.86

modb

0.67

DoubleQuotes

0.65

WindowConstants

0.65

GEBURTS

0.62

heets

0.60

classnames

0.60



0.59

 }^{[

0.59

tamol

0.59

Activations Density 0.394%

numerical data and figures

No Comments

No Known Activations