INDEX

Explanations

references to nodes and their relationship within a programming or data structure context

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

"node" in code or text

np_acts-logits-general · gemini-2.0-flash

node or nodes

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

 Dür

-0.43

 ganha

-0.41

 American

-0.40

the

-0.40

Seven

-0.38

 FirebaseAuth

-0.38

../../

-0.37

American

-0.36

 Gesam

-0.36

Gesam

-0.35

POSITIVE LOGITS

 Node

1.20

 node

1.20

Node

1.15

 Nodes

1.08

 nodes

1.04

 getNode

1.02

 NODE

0.99

node

0.96

getNode

0.94

NODE

0.94

Activations Density 0.084%

references to nodes and their relationship within a programming or data structure context

"node" in code or text

node or nodes

No Comments

No Known Activations