INDEX

Explanations

specific numeric formats and references in a structured dataset or document

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

tagHelper

-0.57

 comigo

-0.49

imwrite

-0.47

hq

-0.46

 Himself

-0.45

 Laplacian

-0.45

Mauri

-0.43

 Chwiliwch

-0.43

 politiet

-0.43

quillas

-0.43

POSITIVE LOGITS

 kaarangay

0.89

 OFDb

0.76

 defaultstate

0.72

 disponibilités

0.70

 parseFrom

0.68

 >=",

0.61

 Roskov

0.59

CrossRef

0.58

HtmlAttribute

0.58

 оригіналу

0.58

Activations Density 0.910%

specific numeric formats and references in a structured dataset or document

No Comments

No Known Activations