INDEX

Explanations

occurrences of the word "list" and related lists in programming contexts

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

 оригіналу

-1.07

 Majefty

-0.97

CloseOperation

-0.97

+#+

-0.95

titleMargin

-0.90

 Monfieur

-0.90

Искәрмәләр

-0.88

tagHelperRunner

-0.85

 Engra

-0.85

twimg

-0.84

POSITIVE LOGITS

 List

1.14

List

1.13

 list

1.03

list

1.02

setList

0.94

 LIST

0.94

LIST

0.90

 itemList

0.87

列表

0.83

getList

0.82

Activations Density 0.054%

occurrences of the word "list" and related lists in programming contexts

No Comments

No Known Activations