INDEX

Explanations

references to personal experiences and preferences related to reading and writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 DialogInterface

-0.62

UnknownFields

-0.61

 initComponents

-0.59

enschappelijke

-0.57

DebuggerNonUser

-0.57

WindowConstants

-0.56

pepe

-0.56

 jsPsych

-0.56

rungsseite

-0.53

SharedDtor

-0.53

POSITIVE LOGITS

 novella

0.79

 novel

0.68

 novels

0.66

Goodreads

0.65

 author

0.64

Author

0.59

 romances

0.59

 romance

0.59

 shifter

0.58

novel

0.58

Activations Density 0.320%

references to personal experiences and preferences related to reading and writing

No Comments

No Known Activations