INDEX

Explanations

terms related to rules and their classifications in a programming or logical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

rody

-0.57

 PUBLISH

-0.55

 Sandal

-0.55

 margins

-0.55

 Mover

-0.52

 Taman

-0.50

 Expl

-0.50

⇑

-0.50

PrintWriter

-0.50

sians

-0.49

POSITIVE LOGITS

 Rules

0.96

Rules

0.96

rules

0.96

 rules

0.94

principalColumn

0.92

 RULES

0.89

 متعلقه

0.88

RULES

0.81

 referenties

0.78

 règles

0.77

Activations Density 0.168%

terms related to rules and their classifications in a programming or logical context

No Comments

No Known Activations