INDEX

Explanations

references to specific locations and entities

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

problems

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

CompilerServices

-0.65

InjectAttribute

-0.57

FXML

-0.45

AutoScaleMode

-0.43

(!__

-0.43

InputBorder

-0.42

ToBounds

-0.41

 alberto

-0.41

ⓧ

-0.41

RUnlock

-0.40

POSITIVE LOGITS

problems

1.49

Problems

1.28

 PROBLEMS

1.25

 Problems

1.25

 problems

1.21

problem

1.05

problemas

1.05

 problèmes

1.00

 Probleme

0.99

 problemen

0.99

Activations Density 0.000%

references to specific locations and entities

problems

No Comments

No Known Activations