INDEX

Explanations

technical terms related to data streams and input/output operations

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

input stream or file source

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

 Numerade

-0.59

EDEFAULT

-0.54

bootstrapcdn

-0.52

⟬

-0.51

IntoConstraints

-0.51

ibrill

-0.50

 Италијани

-0.49

 müſſen

-0.49

RTEE

-0.48

цездатний

-0.48

POSITIVE LOGITS

InputStream

0.45

FileInputStream

0.42

input

0.41

istream

0.40

 upstream

0.37

 iprot

0.37

0.36

Input

0.36

 North

0.35

INPUT

0.34

Activations Density 0.029%

technical terms related to data streams and input/output operations

input stream or file source

No Comments

No Known Activations