INDEX

Explanations

symbols and formatting elements in structured data or code

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

 planète

-0.47

ancey

-0.47

向

-0.45

-0.44

mil

-0.43

 orizz

-0.42

 ioutil

-0.42

 Mixer

-0.42

chlag

-0.41

 cross

-0.41

POSITIVE LOGITS

 typelib

1.05

aarrggbb

0.94

 "..\..\..\

0.91

findpost

0.91

PerformLayout

0.90

WithIOException

0.88

 nahilalakip

0.85

featureID

0.85

adpleegd

0.84

parsedMessage

0.83

Activations Density 0.703%

symbols and formatting elements in structured data or code

No Comments

No Known Activations