INDEX

Explanations

phrases expressing open-ended possibilities or general statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

TagHelpers

-0.89

 arasındaki

-0.83

idopsis

-0.81

sterious

-0.79

órum

-0.77

={`/

-0.76

esgue

-0.76

lgari

-0.75

ณะ

-0.75

PerformLayout

-0.75

POSITIVE LOGITS

 anything

2.22

anything

2.03

 Anything

2.01

Anything

1.99

 ANYTHING

1.70

 everything

1.42

 Everything

1.41

Everything

1.39

everything

1.33

 nothing

1.31

Activations Density 0.070%

phrases expressing open-ended possibilities or general statements

No Comments

No Known Activations