INDEX

Explanations

words and concepts related to privacy and integrity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

FieldBuilder

-0.84

 Reverso

-0.79

inheritDoc

-0.78

 pellic

-0.78

WithIOException

-0.77

 cytos

-0.76

tinyos

-0.75

 dorso

-0.75

 Caballero

-0.74

 Motta

-0.74

POSITIVE LOGITS

Pri

1.22

 Priya

1.10

Pri

1.07

PRI

1.05

pri

1.02

 Prat

1.01

 Pritchard

1.00

 Prit

1.00

pri

0.99

Prat

0.98

Activations Density 0.134%

words and concepts related to privacy and integrity

No Comments

No Known Activations