INDEX

Explanations

technical terms and symbols related to programming or coding

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

 AssemblyCulture

-0.98

 autorytatywna

-0.83

AutoScaleMode

-0.83

 Paglinawan

-0.82

addCriterion

-0.79

WithIOException

-0.77

 CreateTagHelper

-0.76

IntoConstraints

-0.75

ViewFeatures

-0.75

makeConstraints

-0.75

POSITIVE LOGITS

↵↵

0.66

They

0.62

 shouldn

0.62

 They

0.60

It

0.60

You

0.55

It

0.53

Wasn

0.51

The

0.51

There

0.51

Activations Density 5.396%

technical terms and symbols related to programming or coding

No Comments

No Known Activations