INDEX

Explanations

links and references to websites or sources

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

DeleteBehavior

-0.54

WebVitals

-0.53

AndEndTag

-0.52

Tembelea

-0.45

 vapa

-0.41

Smarty

-0.41

 noDo

-0.41

%">

-0.40

amna

-0.39

 nahilalakip

-0.39

POSITIVE LOGITS

invokeLater

0.77

 noqa

0.75

WireFormatLite

0.73

PyExc

0.70

ὴν

0.69

 intptr

0.67

RTEX

0.65

 '\\;'

0.65

lanzen

0.64

globalData

0.64

Activations Density 1.059%

links and references to websites or sources

No Comments

No Known Activations