INDEX

Explanations

blocks of text that contain a variety of numerical or programming symbols and operators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

zie

-0.48

VolleyError

-0.47

zi

-0.45

openzeppelin

-0.44

gre

-0.43

bev

-0.42

kort

-0.42

be

-0.41

...

-0.41

POSITIVE LOGITS

 myſelf

0.77

 Савезне

0.75

bibfield

0.74

enschappelijke

0.73

\{\\

0.70

:✨

0.69

 ProtoMessage

0.68

**/

0.68

'},

0.68

NUMX

0.67

Activations Density 0.368%

blocks of text that contain a variety of numerical or programming symbols and operators

No Comments

No Known Activations