INDEX

Explanations

elements related to programming and data structures in code

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

start of user turn

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

pyplot

-0.52

EventQueue

-0.50

RestController

-0.48

 ReactDOM

-0.46

VertexAttrib

-0.46

ReadLine

-0.45

KommentareTeilen

-0.45

 BrowserModule

-0.44

bibitem

-0.44

 useState

-0.44

POSITIVE LOGITS

only

0.85

 only

0.81

ONLY

0.77

fromLTRB

0.69

 ONLY

0.68

 BoxDecoration

0.66

makeConstraints

0.66

Only

0.66

GEBURTSDATUM

0.65

 лишь

0.64

Activations Density 0.000%

elements related to programming and data structures in code

start of user turn

No Comments

No Known Activations