INDEX

Explanations

technical terms related to computing and electronics

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

hardware and software configurations

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

bsen

-0.40

town

-0.40

GMENT

-0.39

Abs

-0.39

ptor

-0.38

Dice

-0.38

ereq

-0.38

putation

-0.38

hore

-0.37

hota

-0.36

POSITIVE LOGITS

 Савезне

0.51

 Infórmanos

0.43

AccessorTable

0.42

 Réponses

0.42

 bocca

0.41

Portale

0.41

 wireType

0.40

postsleuth

0.40

таратура

0.40

 /></

0.39

Activations Density 0.202%

technical terms related to computing and electronics

hardware and software configurations

No Comments

No Known Activations