INDEX

Explanations

references to methodologies and frameworks in academic or technical 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

ferro

-0.50

盤

-0.50

MessageTagHelper

-0.48

̀n

-0.47

dflare

-0.47

AGH

-0.47

limo

-0.47

 сей

-0.47

Item

-0.46

gemeinde

-0.46

POSITIVE LOGITS

 CreateTagHelper

1.11

GEBURTSDATUM

0.72

تقاوى

0.72

 وتسجيلات

0.69

autorest

0.65

SourceChecksum

0.64

NewUrlParser

0.62

انيف

0.62

GraphicsUnit

0.61

msgSender

0.59

Activations Density 0.693%

references to methodologies and frameworks in academic or technical contexts

No Comments

No Known Activations