INDEX

Explanations

programming-related components and attributes in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.71

de

-0.65

is

-0.65

on

-0.64

ss

-0.62

en

-0.59

in

-0.58

st

-0.56

as

-0.56

POSITIVE LOGITS

tagHelperRunner

3.54

 CreateTagHelper

3.36

MigrationBuilder

3.34

GEBURTSDATUM

3.23

LookAnd

3.19

 resourceCulture

3.08

 EconPapers

3.07

 ProtoMessage

3.03

 ModelExpression

3.02

SourceChecksum

3.02

Activations Density 0.292%

programming-related components and attributes in code

No Comments

No Known Activations