INDEX

Explanations

boolean values indicating conditions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

quehanna

-0.59

resaid

-0.59

helves

-0.56

saco

-0.56

————————————

-0.54

 pier

-0.53

 BaseActivity

-0.53

inafter

-0.52

 Réponses

-0.52

neid

-0.52

POSITIVE LOGITS

true

2.43

 true

1.96

True

1.88

 True

1.68

TRUE

1.68

false

1.59

 TRUE

1.57

 verdadeira

1.25

False

1.21

 verdadera

1.19

Activations Density 0.028%

boolean values indicating conditions or states

No Comments

No Known Activations