INDEX

Explanations

Python function definitions and references

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

حياته

-0.68

حياتها

-0.59

Referències

-0.58

leh

-0.57

Bronnen

-0.55

 Schiff

-0.54

printLine

-0.54

المشاركات

-0.53

aine

-0.53

пиона

-0.52

POSITIVE LOGITS

millimeters

0.72

 démocr

0.68

ftagPool

0.65

ArgsConstructor

0.61

 colorés

0.57

Datuak

0.56

 disponibilità

0.54

fjspx

0.53

ModelSerializer

0.53

NamedQueries

0.52

Activations Density 0.080%

Python function definitions and references

No Comments

No Known Activations