INDEX

Explanations

sections of text that contain specific non-matching information or areas with no significant content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 endblock

-0.88

 lenker

-0.82

 ExecuteAsync

-0.76

 bezeichneter

-0.75

SpringBoot

-0.72

})$}

-0.72

("'"

-0.71

 Obispo

-0.67

 zufolge

-0.66

 typelib

-0.65

POSITIVE LOGITS

 EdgeInsets

3.80

EdgeInsets

1.13

 BorderRadius

0.90

 InputDecoration

0.78

 TextStyle

0.73

sites

0.64

DotNetBar

0.63

 privacy

0.59

Insets

0.59

VOLUME

0.57

Activations Density 0.012%

sections of text that contain specific non-matching information or areas with no significant content

No Comments

No Known Activations