INDEX

Explanations

code-related structures and terms related to data organization

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

 ویکی‌پدی

-0.81

 ExecuteAsync

-0.79

oredCriteria

-0.78

+#+#

-0.77

ReusableCell

-0.76

RenderAtEndOf

-0.76

Personendaten

-0.74

URLException

-0.72

contentLoaded

-0.69

Tikang

-0.69

POSITIVE LOGITS

füh

0.56

führende

0.54

NegativeButton

0.50

SequentialGroup

0.50

 оригіналу

0.48

Segoe

0.47

haviour

0.46

QueryResult

0.46

ilder

0.46

Salta

0.45

Activations Density 0.912%

code-related structures and terms related to data organization

No Comments

No Known Activations