INDEX

Explanations

technical terms and concepts related to coding or programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 selected

-0.53

IZONT

-0.52

 nevertheless

-0.51

 modified

-0.50

afari

-0.50

USR

-0.49

theless

-0.49

pendenti

-0.49

rå

-0.48

ureusement

-0.48

POSITIVE LOGITS

Personendaten

0.80

 createSlice

0.77

脚注の使い方

0.75

ьаж

0.73

providedIn

0.73

SharedDtor

0.70

:✨

0.70

 propOrder

0.68

GEBURTSDATUM

0.63

InvalidProtocol

0.62

Activations Density 2.538%

technical terms and concepts related to coding or programming languages

No Comments

No Known Activations