INDEX

Explanations

occurrences of the prefix "re" in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

re

-2.61

Re

-1.46

re

-1.30

Re

-1.26

ré

-0.94

 ре

-0.94

重新

-0.88

res

-0.84

RE

-0.84

 إعادة

-0.82

POSITIVE LOGITS

queryInterface

0.81

 estekak

0.81

onViewCreated

0.81

UnusedPrivate

0.77

msgTypes

0.77

 betweenstory

0.76

0.75

parsedMessage

0.73

 <>",

0.72

findpost

0.71

Activations Density 0.176%

occurrences of the prefix "re" in words

No Comments

No Known Activations