INDEX

Explanations

indicators of the start and end of a document or code block, as well as specific terms related to programming and data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 '\\;'

-0.81

 مشين

-0.80

 newBuilder

-0.78

Kanpo

-0.77

setVerticalGroup

-0.75

 للمعارف

-0.74

ConstraintMaker

-0.73

 صوتيه

-0.71

StoryboardSegue

-0.70

SourceChecksum

-0.69

POSITIVE LOGITS

netbeans

0.48

baomidou

0.47

 programação

0.45

Vidite

0.45

 funders

0.45

Specifica

0.44

期刊论文

0.44

 Sagan

0.43

感器

0.43

Enciclopedia

0.42

Activations Density 0.236%

indicators of the start and end of a document or code block, as well as specific terms related to programming and data formats

No Comments

No Known Activations