INDEX

Explanations

attributes related to academic referencing and authorship details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.45

бираем

-0.41

朋

-0.41

splitlines

-0.40

pr

-0.38

pr

-0.37

pri

-0.37

tag

-0.36

 near

-0.36

理

-0.35

POSITIVE LOGITS

__(/*!

1.10

Personendaten

1.06

 kaarangay

1.03

 beginnetje

1.01

 EconPapers

1.00

DoubleQuotes

0.98

TagMode

0.95

SourceChecksum

0.94

findpost

0.94

 &___

0.93

Activations Density 0.071%

attributes related to academic referencing and authorship details

No Comments

No Known Activations