INDEX

Explanations

descriptions related to sports players and their performances

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 impra

-1.52

 affor

-1.52

 unden

-1.51

 embodi

-1.51

 depic

-1.50

 increa

-1.49

 pollut

-1.46

 inev

-1.45

 erad

-1.40

 Intere

-1.38

POSITIVE LOGITS

<bos>

0.86

 unfamiliar

0.81

new

0.76

 transition

0.73

 adjustment

0.72

 learning

0.72

 initial

0.72

 welcome

0.70

 initially

0.69

 quickly

0.69

Activations Density 0.484%

descriptions related to sports players and their performances

No Comments

No Known Activations