INDEX

Explanations

the prefix "inf-" followed by suffixes related to legality, such as "ringed" and "idel"

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

requently

-0.52

Kjelder

-0.51

entraînement

-0.44

 Scottish

-0.43

requent

-0.43

 गर्न

-0.42

figuras

-0.42

Aholisi

-0.41

 πάν

-0.41

لاة

-0.40

POSITIVE LOGITS

Inf

1.28

inf

1.21

Inf

1.20

inf

1.12

INF

1.03

 dirait

0.96

 stihl

0.96

 eût

0.94

 vectra

0.93

 constate

0.91

Activations Density 0.087%

the prefix "inf-" followed by suffixes related to legality, such as "ringed" and "idel"

No Comments

No Known Activations