INDEX

Explanations

mathematical terms and constructs

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

PrototypeOf

-0.51

kloped

-0.48

Geografie

-0.48

FieldBuilder

-0.46

ault

-0.42

ByUsername

-0.42

 continues

-0.42

Geh

-0.41

AssignableFrom

-0.41

uves

-0.41

POSITIVE LOGITS

RenderAtEndOf

0.97

MigrationBuilder

0.84

ⓘ

0.78

mybatisplus

0.74

RegressionTest

0.74

 nakalista

0.72

ⓧ

0.70

 SwiftUI

0.69

enterOuterAlt

0.66

]--;

0.66

Activations Density 1.846%

mathematical terms and constructs

No Comments

No Known Activations