INDEX

Explanations

negative outcomes or terminations of projects and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

skjaer

-0.69

hoeddwyd

-0.68

сылкі

-0.66

CELLANEOUS

-0.66

pherals

-0.63

//};

-0.62

principalTable

-0.62

 FishBase

-0.59

bcryptjs

-0.58

bonucleic

-0.57

POSITIVE LOGITS

 altogether

0.90

due

0.85

 entirely

0.81

 completely

0.73

due

0.68

 permanently

0.67

 because

0.67

 kokona

0.65

 abruptly

0.64

 faute

0.60

Activations Density 0.598%

negative outcomes or terminations of projects and relationships

No Comments

No Known Activations