INDEX

Explanations

patterns consisting of repeated characters or symbols, indicative of certain formatting or structure in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

دانشنامهٔ

-0.80

]}$

-0.78

PREDICT

-0.77

✨:

-0.76

AutoField

-0.76

closedir

-0.75

ReusableCell

-0.75

wieś

-0.74

 שוליים

-0.74

énario

-0.71

POSITIVE LOGITS

----------------

1.87

---------------

1.12

------------

1.05

--------------

1.02

-------------

1.01

--------

0.96

-----------

0.95

---------

0.91

------

0.90

-------

0.85

Activations Density 0.268%

patterns consisting of repeated characters or symbols, indicative of certain formatting or structure in the text

No Comments

No Known Activations