INDEX

Explanations

technical terms and identifiers related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 <=",

-0.55

RenderAtEndOf

-0.50

 صوتيه

-0.45

 oprot

-0.40

oredCriteria

-0.40

 unſ

-0.40

 ausge

-0.40

 Parcelable

-0.40

 AssemblyCulture

-0.40

 republic

-0.38

POSITIVE LOGITS

ⓧ

0.59

RegressionTest

0.48

 autorytatywna

0.45

UserScript

0.43

MENAFN

0.42

 obcí

0.42

adpleegd

0.42

 insuffisamment

0.41

ieteur

0.40

SequentialGroup

0.40

Activations Density 0.108%

technical terms and identifiers related to programming and data structures

No Comments

No Known Activations