INDEX

Explanations

references to methodical approaches and their procedural details

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

after numbers or symbols

np_acts-logits-general · gemini-2.0-flash

assimilation doctrine

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

evos

-0.47

enderror

-0.44

unknownFields

-0.43

InputTagHelper

-0.39

addGap

-0.39

 affiliation

-0.39

ItemBackground

-0.39

AnchorTagHelper

-0.38

LayoutStyle

-0.38

LabelTagHelper

-0.38

POSITIVE LOGITS

 espiral

0.41

domada

0.40

jsonwebtoken

0.39

eneuve

0.38

 constitucional

0.38

MENAFN

0.38

ksessa

0.38

Kč

0.38

 restTemplate

0.38

Curator

0.37

Activations Density 0.882%

references to methodical approaches and their procedural details

after numbers or symbols

assimilation doctrine

No Comments

No Known Activations