INDEX

Explanations

specific identifiers or codes related to data structures or elements in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 Paglinawan

-0.97

 שוליים

-0.90

 itſelf

-0.89

rungsseite

-0.81

 NDEBUG

-0.77

 InputDecoration

-0.76

 consultato

-0.75

ſelves

-0.74

pence

-0.72

 Majefty

-0.71

POSITIVE LOGITS

pay

0.56

Pro

0.55

 ErrIntOverflow

0.52

 Selig

0.51

...

0.51

就是要

0.50

<_

0.50

 pick

0.50

 they

0.49

PRO

0.49

Activations Density 0.014%

specific identifiers or codes related to data structures or elements in programming

No Comments

No Known Activations