INDEX

Explanations

references to programming constructs and frameworks

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

__":

-0.92

 للاسماء

-0.78

 myſelf

-0.72

]`

-0.72

 itſelf

-0.71

Хьажоргаш

-0.69

AndEndTag

-0.69

__':

-0.68

'));

-0.66

]};

-0.66

POSITIVE LOGITS

TagHelpers

2.06

AxisAlignment

1.32

ScopeManager

0.97

NgModule

0.84

TagHelper

0.83

 "..\..\..\

0.74

DataAnnotations

0.71

 "..\..\

0.69

contrib

0.65

 BoxFit

0.65

Activations Density 0.002%

references to programming constructs and frameworks

No Comments

No Known Activations