INDEX

Explanations

numbers related to data or statistical references

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

numbered lists and sequences

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UrlEncoded

-0.46

queryInterface

-0.45

setVerticalGroup

-0.44

mycompany

-0.43

 TRANS

-0.42

glTranslatef

-0.40

 defaultstate

-0.40

 miniatur

-0.40

PopMatrix

-0.40

Relacion

-0.39

POSITIVE LOGITS

tagHelperRunner

0.54

httphttps

0.52

enderror

0.47

 nahilalakip

0.46

Demografía

0.44

tagext

0.43

 compleja

0.42

AddTagHelper

0.41

AndEndTag

0.39

})->

0.38

Activations Density 0.102%

numbers related to data or statistical references

numbered lists and sequences

No Comments

No Known Activations