INDEX

Explanations

overall structure or layout elements 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[]:

-0.50

 geschlossen

-0.50

oom

-0.48

FOOTNOTES

-0.47

Tembelea

-0.46

 espec

-0.46

]").

-0.45

tight

-0.45

タル

-0.45

dope

-0.44

POSITIVE LOGITS

prefix

1.22

 prefix

1.19

PREFIX

1.10

 Prefix

1.04

 prefixes

1.00

Prefix

0.99

 PREFIX

0.96

prefixes

0.81

startswith

0.80

 насељу

0.77

Activations Density 0.352%

overall structure or layout elements in the text

No Comments

No Known Activations