INDEX

Model

gemma-2-9b-it

Layer #

Steering Hook

blocks.20.hook_resid_pre

Steering Strength

53.5

Uploader

bot-neuronpedia

Created At

2/15/2025 1:06:43 AM

Raw Vector

Actions

Explanations

punctuation and symbols used in technical writing

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

pyvene/gemma-reft-r1-9b-it-res/l20

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nawr

-0.35

 switch

-0.31

-0.30

DCHECK

-0.29

tua

-0.29

手

-0.29

fetchone

-0.28

 احتم

-0.28

 taha

-0.28

 dizzy

-0.28

POSITIVE LOGITS

 purpoſe

0.66

ſelf

0.65

rrggbb

0.65

ViewInit

0.62

 queſta

0.60

LookAnd

0.59

 raiſ

0.59

 betweenstory

0.58

majánló

0.57

 fubject

0.57

Activations Density 2.810%

punctuation and symbols used in technical writing

No Comments

No Known Activations

punctuation and symbols used in technical writing

No Comments

No Known Activations