INDEX

Explanations

code snippets related to object encoding and decoding 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 @ 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

stdc

-0.50

 verità

-0.49

 rembour

-0.49

Than

-0.49

 normaux

-0.48

atever

-0.48

 than

-0.47

endon

-0.46

 quelconque

-0.46

InitStruct

-0.46

POSITIVE LOGITS

0.80

uxxxx

0.75

ftagPool

0.71

 AssemblyProduct

0.71

<?

0.66

 VizieR

0.64

__[

0.63

dispatch

0.62

Activations Density 0.099%

code snippets related to object encoding and decoding in a programming context

No Comments

No Known Activations