INDEX

Explanations

punctuation marks and brackets

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

homonymie

-0.69

 subgraph

-0.57

 Pompey

-0.52

IonicModule

-0.51

 Antilles

-0.51

 kræ

-0.49

aze

-0.49

 Sigism

-0.48

ử

-0.47

 Majest

-0.47

POSITIVE LOGITS

GraphicsUnit

0.85

AndEndTag

0.81

[++

0.79

LookAnd

0.75

bootstrapcdn

0.73

InputBorder

0.72

reactstrap

0.71

 protoimpl

0.71

readAs

0.71

 utafitiHapana

0.68

Activations Density 0.284%

punctuation marks and brackets

No Comments

No Known Activations