INDEX

Explanations

indicators of structured data elements or modules

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

enumi

-0.50

<?

-0.49

 <<<<<<<<<<<<<<

-0.48

webElementXpaths

-0.48

SequentialGroup

-0.48

WriteAttribute

-0.47

DBNull

-0.47

 mijne

-0.47

jsonwebtoken

-0.46

 שוליים

-0.46

POSITIVE LOGITS

ApiController

3.16

 ControllerBase

0.71

Api

0.71

Api

0.71

Controller

0.66

ApiRequest

0.65

controller

0.64

 Controller

0.64

ApiException

0.64

ApiService

0.61

Activations Density 0.000%

indicators of structured data elements or modules

No Comments

No Known Activations