INDEX

Explanations

words related to visibility and invisibility

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yntaxException

-0.94

principalColumn

-0.80

 endwhile

-0.79

@"/

-0.78

 Rowley

-0.76

={`/

-0.73

ряда

-0.70

 numele

-0.70

 Parma

-0.70

ChromeDriver

-0.70

POSITIVE LOGITS

 visible

2.02

 Visible

2.00

visible

1.94

Visible

1.89

 visibles

1.81

 Visibility

1.78

VISIBLE

1.68

 visibility

1.66

Visibility

1.57

VIS

1.48

Activations Density 0.061%

words related to visibility and invisibility

No Comments

No Known Activations