INDEX

Explanations

references to labels or tags and their placement information

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

signs and labels

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

AddTagHelper

-0.49

帖最后由

-0.48

SpringBootTest

-0.38

IActionResult

-0.38

 setuptools

-0.38

UrlResolution

-0.36

PRWEB

-0.36

 soma

-0.36

PyTuple

-0.34

isSuccessful

-0.32

POSITIVE LOGITS

 nahilalakip

0.49

Derbyniad

0.47

WebElementEntity

0.47

printed

0.45

 printed

0.45

ftone

0.45

 desvan

0.44

atellite

0.44

webElementXpaths

0.43

Бахар

0.43

Activations Density 0.048%

references to labels or tags and their placement information

signs and labels

No Comments

No Known Activations