INDEX

Explanations

phrases and contexts indicating causation or conditions

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

ніципалі

-0.87

 Theſe

-0.83

Efq

-0.82

 Monfieur

-0.81

 AttributeSet

-0.79

 Majefty

-0.78

 ―――――

-0.76

 étr

-0.74

:✨

-0.72



-0.71

POSITIVE LOGITS

due

0.94

 because

0.89

 devido

0.88

 Because

0.84

由于

0.84

由於

0.82

Because

0.81

 بسبب

0.80

是因为

0.80

 debido

0.80

Activations Density 0.134%

phrases and contexts indicating causation or conditions

No Comments

No Known Activations