INDEX

Explanations

structures and elements related to input configurations in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 bőr

-0.53

imetric

-0.50

цин

-0.50

 udaler

-0.49

 varargin

-0.49

 administrativos

-0.48

 "'";

-0.46

 timeval

-0.46

specialchars

-0.46

TabbedPane

-0.46

POSITIVE LOGITS

 Meksiku

0.69

dart

0.65

("${

0.64

Personendaten

0.64

~/

0.60

=>

0.60

'${

0.60

 freezed

0.60

💼

0.60

 Wicidata

0.57

Activations Density 0.192%

structures and elements related to input configurations in programming

No Comments

No Known Activations