INDEX

Explanations

phrases or terms that establish a foundational or underlying concept

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

basis for or of

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Monfieur

-0.57

 Electrochemical

-0.50

WebServlet

-0.50

Pyrene

-0.48

WebMethod

-0.48

oflu

-0.47

 Electromagnetic

-0.47

 peregr

-0.46

 Houſe

-0.46

ientras

-0.45

POSITIVE LOGITS

 basis

2.28

 Basis

2.22

Basis

2.14

basis

2.14

 BASIS

2.05

 Grundlage

1.30

 bases

1.23

 Bases

1.13

bases

1.05

Bases

1.01

Activations Density 0.012%

phrases or terms that establish a foundational or underlying concept

basis for or of

No Comments

No Known Activations