INDEX

Explanations

mentions of rules and regulations

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

"rule" or "rules"

np_acts-logits-general · gemini-2.0-flash

rules and their application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

encounter

-0.45

 Langen

-0.45

 McPherson

-0.45

 Whitehead

-0.43

perhaps

-0.43

 geschenk

-0.43

 României

-0.43

 Gefähr

-0.43

bigint

-0.43

printStackTrace

-0.43

POSITIVE LOGITS

 rule

1.12

 Rule

1.08

 rules

1.05

 RULE

1.04

Rule

1.02

 Rules

1.00

RULE

0.96

rule

0.96

Rules

0.91

rules

0.89

Activations Density 0.257%

mentions of rules and regulations

"rule" or "rules"

rules and their application

No Comments

No Known Activations