INDEX

Explanations

elements related to cause and effect relationships or influence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

<eos>

-0.54

RegistryLite

-0.50

-0.48

Manbalar

-0.48

-0.44

WillAppear

-0.43

-0.42

",

-0.42

""

-0.42

POSITIVE LOGITS

 gynhyrchwyd

0.90

ⓧ

0.86

UnsafeEnabled

0.84

 صوتيه

0.81

期刊论文

0.80

moiselle

0.80

 userSchema

0.79

 nakalista

0.78

actéristique

0.77

 Anſ

0.77

Activations Density 1.562%

elements related to cause and effect relationships or influence in various contexts

No Comments

No Known Activations