INDEX

Explanations

sections related to errors or issues in hardware or programming

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

Code snippets or program paths

np_acts-logits-general · gemini-2.0-flash

code snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ModelAttribute

-0.69

 Weiss

-0.64

 FontWeight

-0.63

'@/

-0.62

 Appel

-0.60

 BorderRadius

-0.58

andola

-0.58

lobo

-0.57

 Kowalski

-0.56

 UIButton

-0.56

POSITIVE LOGITS

</tr>

1.00

↵

0.89

0.84

[toxicity=0]

0.83

0.76

<tbody>

0.76

<tr>

0.76

}}$\\

0.74

PerformLayout

0.73

."</

0.73

Activations Density 1.158%

sections related to errors or issues in hardware or programming

Code snippets or program paths

code snippets

No Comments

No Known Activations

sections related to errors or issues in hardware or programming

Code snippets or program paths

code snippets

No Comments

No Known Activations