INDEX

Explanations

numerical values and related characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

__*/

-0.54

遍

-0.45

ñador

-0.45

startIndex

-0.41

 covering

-0.41

zato

-0.41

or

-0.41

سخ

-0.40

 vecchio

-0.40

bori

-0.40

POSITIVE LOGITS

脚注の使い方

1.01

ThroughAttribute

0.82

 дописавши

0.80

 propOrder

0.79

 autorytatywna

0.76

 kasarigan

0.74

BufferException

0.69

TypedDataSet

0.67

AddTagHelper

0.67

VIAF

0.67

Activations Density 0.197%

numerical values and related characters

No Comments

No Known Activations