INDEX

Explanations

occurrences of the word "lock" and its variations or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 MainAxisSize

-0.77

MessageTagHelper

-0.73

 stället

-0.71

 vägen

-0.71

 OFDb

-0.71

 vétérina

-0.68

 medlems

-0.67

sega

-0.66

 varandra

-0.65

 vulga

-0.63

POSITIVE LOGITS

 lock

2.38

lock

2.31

Lock

2.19

 Lock

2.16

 locks

1.99

 LOCK

1.88

LOCK

1.76

locks

1.68

 Locks

1.65

 locked

1.52

Activations Density 0.059%

occurrences of the word "lock" and its variations or related terms

No Comments

No Known Activations