INDEX

Explanations

specific nouns and proper nouns that are significant within a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

SourceChecksum

-0.61

po

-0.51

BASEPATH

-0.47

cy

-0.46

tr

-0.46

Cy

-0.44

+#+#

-0.44

Cat

-0.41

\[

-0.40

cat

-0.39

POSITIVE LOGITS

 Мексичка

0.89

 fallu

0.85

RegressionTest

0.84

</thead>

0.84

 initComponents

0.81

ksikon

0.80

 تضيفلها

0.77

 jScrollPane

0.76

^(@)

0.76

 postIndex

0.74

Activations Density 0.937%

specific nouns and proper nouns that are significant within a given context

No Comments

No Known Activations