INDEX

Explanations

comments and engagement indicators in texts

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

LookAnd

-0.87

 tartalomajánló

-0.85

 MainAxisSize

-0.79

 pleaſure

-0.75

 itſelf

-0.73

 greateſt

-0.72

 RSSSF

-0.70

 neceff

-0.70

Efq

-0.69

 Jefus

-0.69

POSITIVE LOGITS

مصادر

0.57

aarrggbb

0.52

<eos>

0.49

0.48

↵

0.48

imod

0.47

ⓧ

0.46

↵↵

0.45

PROTOBUF

0.45

</h2>

0.44

Activations Density 0.522%

comments and engagement indicators in texts

No Comments

No Known Activations