INDEX

Explanations

code-related syntax or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ModelForm

-0.57

 springfox

-0.50

devamını

-0.50

行政区划

-0.49

 viewDidLoad

-0.48

NameInMap

-0.47

évaluateur

-0.47

ijo

-0.47

 Future

-0.47

 "..\..\

-0.47

POSITIVE LOGITS

let

1.48

const

1.20

let

1.11

LET

0.93

 const

0.90

var

0.86

LET

0.78

 letting

0.77

Let

0.77

 lets

0.74

Activations Density 0.119%

code-related syntax or structures

No Comments

No Known Activations