INDEX

Explanations

phrases and terms related to awareness and understanding of various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Quig

-0.62

войства

-0.61

 Pickering

-0.61

bcryptjs

-0.61

 Biggs

-0.61

://

-0.59

 Schultz

-0.59

bakken

-0.57

Sp

-0.56

QUADS

-0.56

POSITIVE LOGITS

 awareness

1.78

 Aware

1.73

 aware

1.70

awareness

1.65

 Awareness

1.65

Awareness

1.60

aware

1.53

Aware

1.28

wareness

1.26

 consciousness

1.14

Activations Density 0.059%

phrases and terms related to awareness and understanding of various issues

No Comments

No Known Activations