INDEX

Explanations

function definitions and calls

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

置

-0.64

mens

-0.64

ment

-0.63

ity

-0.62

ます

-0.62

-0.59

scriptcase

-0.58

ical

-0.58

Mst

-0.57

POSITIVE LOGITS

RetentionPolicy

0.94

ScopeManager

0.84

 للمعارف

0.82

|}{\

0.81

AsUp

0.81

atemala

0.80

LikeLike

0.80

 headless

0.80

 calldata

0.79

wahati

0.79

Activations Density 0.122%

function definitions and calls

No Comments

No Known Activations