INDEX

Explanations

programming-related terms and components

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

 InputDecoration

-0.63

 الرخصة

-0.58

writeFieldEnd

-0.56

FileDescriptor

-0.55

ächlich

-0.54

 depositphotos

-0.53

principalTable

-0.52

 pleaſure

-0.51

setObjectName

-0.50

 consort

-0.50

POSITIVE LOGITS

Архівовано

0.59

 تضيفلها

0.59

lahraga

0.59

 CURIAM

0.59

amse

0.58

 Chwiliwch

0.56

原始内容存档于

0.56

 <<<<<<<<<<<<<<

0.56

jména

0.56

XtraReports

0.55

Activations Density 0.018%

programming-related terms and components

No Comments

No Known Activations