INDEX

Explanations

concepts related to awareness and perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

posób

-0.66

bcryptjs

-0.64

din

-0.61

 Quig

-0.60

(!__

-0.60

 Schultz

-0.60

Dut

-0.60

fertigung

-0.60

clusal

-0.60

anadium

-0.59

POSITIVE LOGITS

 awareness

1.58

 Aware

1.48

 aware

1.45

awareness

1.42

 Awareness

1.41

Awareness

1.41

aware

1.36

Aware

1.11

wareness

1.04

 consciousness

0.99

Activations Density 0.047%

concepts related to awareness and perception

No Comments

No Known Activations