INDEX

Explanations

programming-related terms and 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

 praised

-0.37

 Künstler

-0.37

 artist

-0.36

OGND

-0.35

 purified

-0.35

 artists

-0.35

NewUrlParser

-0.35

 studied

-0.34

Становништво

-0.34

 chatted

-0.34

POSITIVE LOGITS

 propOrder

0.68

zzleHttp

0.58

Personendaten

0.54

simpleType

0.52

ContentAsync

0.52

SBATCH

0.52

MessageTagHelper

0.52

 protoimpl

0.50

featureID

0.50

IConfiguration

0.48

Activations Density 0.019%

programming-related terms and structures

No Comments

No Known Activations