INDEX

Explanations

properties or attributes defined in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 otomatig

-0.80

 '\\;'

-0.77

LookAnd

-0.76

}{*}{

-0.75

mybatisplus

-0.72

|}{$

-0.71

OGND

-0.69

<bos>

-0.69

:\/\/

-0.69

parsedMessage

-0.69

POSITIVE LOGITS

mandu

0.60

HideInInspector

0.58

Getter

0.51

preventDefault

0.49

 viewDidLoad

0.47

nocache

0.46

0.45

 afspraak

0.45

سری

0.45

quiao

0.44

Activations Density 0.009%

properties or attributes defined in a programming context

No Comments

No Known Activations